The increased focus on sustainability in response to climate change has given rise to many new initiatives to meet the rise in building load demand. The concept of distributed energy resources (DER) and optimal control of supply to meet power demands in buildings have resulted in growing interest to adopt microgrids for a precinct or a university campus. In this paper, a model for an actual physical microgrid has been constructed in OPAL-RT for real-time simulation studies. The load demands for SIT@NYP campus and its weather data are collected to serve as input to run on the digital twin model of DERs of the microgrid. The dynamic response of the microgrid model in response to fluctuations in power generation due to intermittent solar PV generation and load demands are examined via real-time simulation studies and compared with the response of the physical assets. It is observed that the simulation results match closely to the performance of the actual physical asset. As such, the developed microgrid model offers plug-and-play capability, which will allow power providers to better plan for on-site deployment of renewable energy sources and energy storage to match the expected building energy demand.

Detection of partial discharge (PD) in switchgears requires extensive data collection and time-consuming analyses. Data from real live operational environments pose great challenges in the development of robust and efficient detection algorithms due to overlapping PDs and the strong presence of random white noise. This paper presents a novel approach using clustering for data cleaning and feature extraction of phase-resolved partial discharge (PRPD) plots derived from live operational data. A total of 452 PRPD 2D plots collected from distribution substations over a six-month period were used to test the proposed technique. The output of the clustering technique is evaluated on different types of machine learning classification techniques and the accuracy is compared using balanced accuracy score. The proposed technique extends the measurement abilities of a portable PD measurement tool for diagnostics of switchgear condition, helping utilities to quickly detect potential PD activities with minimal human manual analysis and higher accuracy.

Spectrogram-based representations have grown to dominate the feature space for deep learning audio analysis systems, and are often adopted for speech analysis also. Initially, the primary motivation behind spectrogram-based representations was their ability to present sound as a two-dimensional signal in the time–frequency plane, which not only provides an interpretable physical basis for analysing sound, but also unlocks the use of a range of machine learning techniques such as convolutional neural networks, which had been developed for image processing. A spectrogram is a matrix characterised by the resolution and span of its dimensions, as well as by the representation and scaling of each element. Many possibilities for these three characteristics have been explored by researchers across numerous application areas, with different settings showing affinity for various tasks. This paper reviews the use of spectrogram-based representations and surveys the state-of-the-art to question how front-end feature representation choice allies with back-end classifier architecture for different tasks.

Background: Life-space mobility (LSM) refers to the movement of people over time and the areas through which they move to achieve life goals of health, employment, security, and participation for active aging. Objective: The Elderly Activity Life-Space Envelopes program is a large interdisciplinary mixed methods LSM study in older adults of 50 years and above. The overarching aims were to discover why, where, and when older adults travel and how they get to their destinations. Methods: In this paper, we focus on the methodology of the main quantitative phase. This community-based study comprised an in-person multidomain geriatric assessment with physical performance measures, followed by a 14-day travel diary. For the multidomain geriatric assessment, we structurally underpinned important population health constructs including the WHO International Classification of Functioning, Disability and Health, Frailty, and Intrinsic Capacity. We also described home meso-environments by incorporating authoritative open-source environmental attributes. These facilitated the categorization of LSM determinants into health, social, and environmental domains. The LSM outcomes include self-reported and objective geographical information science LSM measures. We further developed a suite of geographical information science LSM outcomes in alignment with our overarching aims. Quota sampling based on age groups, housing typology, and frailty status was applied. A customized, smartphone-based digital travel diary was designed, and barometric sensors were enabled to capture 3D LSM in capable smartphones. Results: We recruited 1131 older adults with an average age of 63.8 (SD 7.6) years. The large majority (n=1062, 95%) successfully documented their travel diary on their smartphones with the rest on paper-based travel diaries. For the digital data, a total of 88,166 node points were recorded. There were 76,741 trips and 106,323 trip legs documented through the e-travel diary platform. Valid vertical LSM data were obtained from 228 participants. The majority (n=842, 75%) lived in public apartments, and 29% (n=326) were prefrail or frail. Conclusions: We provide a practical, feasible yet comprehensive protocol integrating LSM within important population health themes. Also, the development of an objective, systematic outcomes framework will form the basis for future LSM studies in the field. We aim to analyze the interactions between LSM outcomes, explore its diverse determinants, and identify senior travel phenotypes. We hope to develop interdisciplinary policy−driven interventions to ultimately improve the quality of life in older adults.