We use cookies to analyze the browsing and usage of our website and to personalize your experience. You can disable these technologies at any time, but this may limit certain functionalities of the site. Read our Privacy Policy for more information.
Setting cookies
You can enable and disable the types of cookies you wish to accept. However certain choices you make could affect the services offered on our sites (e.g. suggestions, personalised ads, etc.).
Essential cookies
These cookies are necessary for the operation of the site and cannot be deactivated. (Still active)
Analytics cookies
Do you accept the use of cookies to measure the audience of our sites?
Multimedia Player
Do you accept the use of cookies to display and allow you to watch the video content hosted by our partners (YouTube, etc.)?
Publications
The end game: respecting major sources of population diversity
Joint Embedding Self-Supervised Learning (JE-SSL) has seen rapid developments in recent years, due to its promise to effectively leverage la… (see more)rge unlabeled data. The development of JE-SSL methods was driven primarily by the search for ever increasing downstream classification accuracies, using huge computational resources, and typically built upon insights and intuitions inherited from a close parent JE-SSL method. This has led unwittingly to numerous pre-conceived ideas that carried over across methods e.g. that SimCLR requires very large mini batches to yield competitive accuracies; that strong and computationally slow data augmentations are required. In this work, we debunk several such ill-formed a priori ideas in the hope to unleash the full potential of JE-SSL free of unnecessary limitations. In fact, when carefully evaluating performances across different downstream tasks and properly optimizing hyper-parameters of the methods, we most often -- if not always -- see that these widespread misconceptions do not hold. For example we show that it is possible to train SimCLR to learn useful representations, while using a single image patch as negative example, and simple Gaussian noise as the only data augmentation for the positive pair. Along these lines, in the hope to democratize JE-SSL and to allow researchers to easily make more extensive evaluations of their methods, we introduce an optimized PyTorch library for SSL.
Inference time, model size, and accuracy are critical for deploying deep neural network models. Numerous research efforts have been made to … (see more)compress neural network models with faster inference and higher accuracy. Pruning and quantization are mainstream methods to this end. During model quantization, converting individual float values of layer weights to low-precision ones can substantially reduce the computational overhead and improve the inference speed. Many quantization methods have been studied, for example, vector quantization, low-bit quantization, and binary/ternary quantization. This survey focuses on ternary quantization. We review the evolution of ternary quantization and investigate the relationships among existing ternary quantization methods from the perspective of projection function and optimization methods.
The renewable power has been widely used in modern cloud data centers, which also produce large electricity bills and the negative impacts o… (see more)n environments. However, frequent fluctuation and intermittency of renewable power often cause the challenges in terms of the stability of both electricity grid and data centers, as well as decreasing the utilization of renewable power. Existing schemes fail to alleviate the renewable power fluctuation, which is caused by the essential properties of renewable power. In order to address this problem, we propose an efficient and easy-to-use smooth renewable power-aware scheme, called Smoother, which consists of Flexible Smoothing (FS) and Active Delay (AD). First, in order to smooth the fluctuation of renewable power, FS carries out the optimized charge/discharge operation via computing the minimum variance of the renewable power that is supplied to data centers per interval. Second, AD improves the utilization of renewable power via actively adjusting the execution time of deferrable workloads. Extensive experimental results via examining the traces of real-world data centers demonstrate that Smoother significantly reduces the negative impact of renewable power fluctuations on data centers and improves the utilization of renewable power by 250.88 percent on average. We have released the source codes for public use.
This article presents an extended state space model for aggregation of large-scale electric vehicles (EVs) for frequency regulation and peak… (see more) load shaving in power systems. The proposed model systematically deals with the fast charging of EVs as an effective solution for immediate charging requirements. Furthermore, the proposed extended state space model increases the flexibility of the EV aggregator (EVA) by enabling the EVs to participate in ancillary services with both regular and fast charging/discharging rates. This will help the EVA to provide a prompt and efficient response to severe generation-consumption imbalances. A probabilistic control approach is developed which reduces the communication burden of the EVA. Furthermore, the uncertainties related to EV users' behavior are modeled in real-time. The simulations are conducted for a typical power system including a large population of EVs, a conventional generator (CG), and a wind generation system. It is shown that the proposed aggregation model can accurately describe the aggregated behavior of a large population of EVs enabling them to efficiently participate in frequency regulation and peak load shaving services. Finally, the performance of EVA is evaluated for different driving behaviors and state of charge (SOC) levels of the EV population.
2023-03-01
IEEE Transactions on Transportation Electrification (published)
