Chenghao Huang

This paper introduces the design and implementation of a two-wheel inverted pendulum (TWIP) system with a fuzzy control scheme and the system-on-a-programmable-chip (SoPC) technology. The control scheme includes three kinds of fuzzy controls which are the fuzzy balanced standing control (FBSC), the fuzzy traveling and position control (FTPC), and the fuzzy yaw steering control (FYSC). Based on the Takagi-Sugeno fuzzy model of the TWIP, the FBSC is a structure of a parallel distributed compensator solved by the linear matrix inequality approach. Based on the motion characteristic of the TWIP, the FTPC and the FYSC are designed with Mamdani architecture if-then rules. Furthermore, the fuzzy control scheme for the real TWIP is implemented into an SoPC development board with an embedded reduced-instruction-set-computer soft-core processor and user intellectual property modules. Both the computer simulations and practical experiments demonstrate the effectiveness of the proposed control scheme.

Foundation models, such as Large Language Models (LLMs), can respond to a wide range of format-free queries without any task-specific data collection or model training, creating various research and application opportunities for the modeling and operation of large-scale power systems. In this paper, we outline how such large foundation model such as GPT-4 are developed, and discuss how they can be leveraged in challenging power and energy system tasks. We first investigate the potential of existing foundation models by validating their performance on four representative tasks across power system domains, including the optimal power flow (OPF), electric vehicle (EV) scheduling, knowledge retrieval for power engineering technical reports, and situation awareness. Our results indicate strong capabilities of such foundation models on boosting the efficiency and reliability of power system operational pipelines. We also provide suggestions and projections on future deployment of foundation models in power system applications.

Social media is an indispensable part of modern life, and social media popularity prediction (SMPP) plays a vital role in practice. In current work, the inconsistency of words in labels and titles, user feature transformation, etc have not been well noticed. In this paper, we propose a novel approach named Title-and-Tag Contrastive Vision-and-Language Transformer (TTC-VLT), combining two pre-trained vision and language transformers and other two dense feature parts for this prediction task. On one hand, in order to learn the differences between titles and tags, we design title-tag contrastive learning for title-visual and tag-visual, which separately extracts multimodal information from two types of text. On the other hand, user identification features are transformed to embedding vectors to capture user attribute details. From the extensive experiments, our approach outperforms the other methods on the social media prediction dataset. Our team achieve the 2nd place on the leader board of the Social Media Prediction Challenge 2022.

The paper proposes a novel fuzzy observer synthesis for the Takagi–Sugeno (T–S) fuzzy system with uncertainty and output disturbance. First, an augmented fuzzy model is built by integrating the system state and the output disturbance into a new variable. Then, based on Lyapunov theory and LMIs tools, two main theorems are derived for particular and general cases of fuzzy systems, respectively. In each main theorem, three key conditions are proposed, under which the fuzzy observer is synthesized to estimate the system state and the output disturbance simultaneously. According to the main theorems, a methodical procedure for the fuzzy observer synthesis is also provided. Finally, the effectiveness of the observer is demonstrated by a numerical example.

Short-term load forecasting (STLF) plays a pivotal role in operational efficiency of power plants. Leveraging data from utility companies for STLF in a wholesale market presents challenges. Notably, data sharing reluctance from utility companies, driven by privacy considerations, limits the availability of valuable forecasting information. Concurrently, due to the growing reliance on information and communication technologies, data integrity attacks (DIAs) and communication noise are emerging as a significant concern, which is largely overlooked in existing research. We propose an innovative approach combining deep reinforcement learning (DRL) with federated learning (FL) to construct a robust STLF model that meets privacy constraints and operates efficiently. By employing FL, we facilitate collaboration between the power plant and multiple utility companies to generate a STLF model for the power plant, circumventing the need for direct access to raw data from utility companies, thereby preserving data privacy. To counteract model degradation induced by DIAs and noise in communication channels, we incorporate DRL into our methodology. Simulation outcomes affirm the efficacy of our proposed approach, demonstrating its capacity to deliver accurate and resilient STLF for power plants, even in the presence of DIAs and communication noise.