Wenjun Tang

Guodong Yin, Mufeng Zhou, Yiming Chen et al.

Performing data-intensive tasks in the von Neumann architecture is challenging to achieve both high performance and power efficiency due to the memory wall bottleneck. Computing-in-memory (CiM) is a promising mitigation approach by enabling parallel in-situ multiply-accumulate (MAC) operations within the memory with support from the peripheral interface and datapath. SRAM-based charge-domain CiM (CD-CiM) has shown its potential of enhanced power efficiency and computing accuracy. However, existing SRAM-based CD-CiM faces scaling challenges to meet the throughput requirement of high-performance multi-bit-quantization applications. This paper presents an SRAM-based high-throughput ReLU-optimized CD-CiM macro. It is capable of completing MAC and ReLU of two signed 8b vectors in one CiM cycle with only one A/D conversion. Along with non-linearity compensation for the analog computing and A/D conversion interfaces, this work achieves 51.2GOPS throughput and 10.3TOPS/W energy efficiency, while showing 88.6% accuracy in the CIFAR-10 dataset.

Kuan-Cheng Lee, Hong-Tzer Yang, Wenjun Tang

Demand response (DR), as one of the important energy resources in the future's grid, provides the services of peak shaving, enhancing the efficiency of renewable energy utilization with a short response period, and low cost. Various categories of DR are established, e.g. automated DR, incentive DR, emergency DR, and demand bidding. However, with the practical issue of the unawareness of residential and commercial consumers' utility models, the researches about demand bidding aggregator involved in the electricity market are just at the beginning stage. For this issue, the bidding price and bidding quantity are two required decision variables while considering the uncertainties due to the market and participants. In this paper, we determine the bidding and purchasing strategy simultaneously employing the smart meter data and functions. A two-agent deep deterministic policy gradient method is developed to optimize the decisions through learning historical bidding experiences. The online learning further utilizes the daily newest bidding experience attained to ensure trend tracing and self-adaptation. Two environment simulators are adopted for testifying the robustness of the model. The results prove that when facing diverse situations the proposed model can earn the optimal profit via off/online learning the bidding rules and robustly making the proper bid.

Zichao Meng, Ye Guo, Wenjun Tang et al.

A multivariate density forecast model based on deep learning is designed in this paper to forecast the joint cumulative distribution functions (JCDFs) of multiple security margins in power systems. Differing from existing multivariate density forecast models, the proposed method requires no a priori hypotheses on the distribution of forecasting targets. In addition, based on the universal approximation capability of neural networks, the value domain of the proposed approach has been proven to include all continuous JCDFs. The forecasted JCDF is further employed to calculate the deterministic security assessment index evaluating the security level of future power system operations. Numerical tests verify the superiority of the proposed method over current multivariate density forecast models. The deterministic security assessment index is demonstrated to be more informative for operators than security margins as well.

Wenjun Tang, Hao Wang, Xian-Long Lee et al.

The smart meter data analysis contributes to better planning and operations for the power system. This study aims to identify the drivers of residential energy consumption patterns from the socioeconomic perspective based on the consumption and demographic data using machine learning. We model consumption patterns by representative loads and reveal the relationship between load patterns and socioeconomic characteristics. Specifically, we analyze the real-world smart meter data and extract load patterns by clustering in a robust way. We further identify the influencing socioeconomic attributes on load patterns to improve our method's interpretability. The relationship between consumers' load patterns and selected socioeconomic features is characterized via machine learning models. The findings are as follows. (1) Twelve load clusters, consisting of six for weekdays and six for weekends, exhibit a diverse pattern of lifestyle and a difference between weekdays and weekends. (2) Among various socioeconomic features, age and education level are suggested to influence the load patterns. (3) Our proposed analytical model using feature selection and machine learning is proved to be more effective than XGBoost and conventional neural network model in mapping the relationship between load patterns and socioeconomic features.