Search for: All records

Space cooling constitutes >10% of worldwide electricity consumption and is anticipated to rise swiftly due to intensified heatwaves under emerging climate change. The escalating electricity demand for cooling services will challenge already stressed power grids, especially during peak times of demand. To address this, the adoption of demand response to adjust building energy use on the end-user side becomes increasingly important to adapt future smart buildings with rapidly growing renewable energy sources. However, existing demand response strategies predominantly explore sensible cooling energy as flexible building load while neglecting latent cooling energy, which constitutes significant portions of total energy use of buildings in humid climates. Hence, this paper aims to evaluate the demand response potential by adjusting latent cooling energy through ventilation control for typical medium commercial office buildings in four representative cities across different humid climate zones, i.e., Miami, Huston, Atlanta, and New York in the United States (US). As the first step, the sensible heat ratio, defined as sensible cooling load to total building load (involving both sensible and latent load), in different humid climates are calculated. Subsequently, the strategy to adjust building latent load through ventilation control (LLVC) is explored and implemented for demand response considering the balance of energy shifting, indoor air quality, and energy cost. Results reveal that adjusting building ventilation is capable of achieving 30%–40% Heating, Ventilation, and Air-conditioning (HVAC) cooling demand flexibility during HVAC operation while among this, the latent cooling energy contributes 56% ~ 66.4% to the overall demand flexibility. This work provides a feasible way to improve electricity grid flexibility in humid climates, emphasizing the significant role of adjusting latent cooling energy in building demand response. 

The increasing uncertainty of distributed energy resources promotes the risks of transient events for power systems. To capture event dynamics, Phasor Measurement Unit (PMU) data is widely utilized due to its high resolutions. Notably, Machine Learning (ML) methods can process PMU data with feature learning techniques to identify events. However, existing ML-based methods face the following challenges due to salient characteristics from both the measurement and the label sides: (1) PMU streams have a large size with redundancy and correlations across temporal, spatial, and measurement type dimensions. Nevertheless, existing work cannot effectively uncover the structural correlations to remove redundancy and learn useful features. (2) The number of event labels is limited, but most models focus on learning with labeled data, suffering risks of non-robustness to different system conditions. To overcome the above issues, we propose an approach called Kernelized Tensor Decomposition and Classification with Semi-supervision (KTDC-Se). Firstly, we show that the key is to tensorize data storage, information filtering via decomposition, and discriminative feature learning via classification. This leads to an efficient exploration of structural correlations via high-dimensional tensors. Secondly, the proposed KTDC-Se can incorporate rich unlabeled data to seek decomposed tensors invariant to varying operational conditions. Thirdly, we make KTDC-Se a joint model of decomposition and classification so that there are no biased selections of the two steps. Finally, to boost the model accuracy, we add kernels for non-linear feature learning. We demonstrate the KTDC-Se superiority over the state-of-the-art methods for event identification using PMU data. 

Under the trend of deeper renewable energy integration, active distribution networks are facing increasing uncertainty and security issues, among which the arcing fault detection (AFD) has baffled researchers for years. Existing machine learning based AFD methods are deficient in feature extraction and model interpretability. To overcome these limitations in learning algorithms, we have designed a way to translate the non-transparent machine learning prediction model into an implementable logic for AFD. Moreover, the AFD logic is tested under different fault scenarios and realistic renewable generation data, with the help of our self-developed AFD software. The performance from various tests shows that the interpretable prediction model has high accuracy, dependability, security and speed under the integration of renewable energy.