Wenting Zhao

The microgrid trading market can effectively solve the problem of in-situ consumption of distributed energy and reduce the impact of distributed generation (DG) on the grid. However, the traditional microgrid trading model has some shortcomings, such as high operation cost and poor security. Therefore, in this paper, a microgrid market trading model was developed using consortium blockchain technology and Nash game equilibrium theory. Firstly, blockchain container is used to authenticate the users who want to participate in the transaction. Then, the pricing system collects and integrates transaction requests submitted by users, then formulates transaction pricing strategy of microgrid using Nash equilibrium theory. Finally, the price, trading volume, and user information are submitted to the blockchain container for transaction matching to achieve the transaction. After the transaction is completed, its related information is recorded in the hyperledger and the dispatch system is called. The scene simulation was implemented on Fabric 1.1 platform and the results analyzed. Results show that the trading model proposed in this paper greatly reduces the cost of electricity purchase and improves the benefits of electricity sales. Besides, the model is far more capable of handling transactions than the models based on Bitcoin and Ethereum.

Multimodal sentiment analysis has attracted increasing attention and lots of models have been proposed. However, the performance of the state-of-the-art models decreases sharply when they are deployed in the real world. We find that the main reason is that real-world applications can only access the text outputs by the automatic speech recognition (ASR) models, which may be with errors because of the limitation of model capacity. Through further analysis of the ASR outputs, we find that in some cases the sentiment words, the key sentiment elements in the textual modality, are recognized as other words, which makes the sentiment of the text change and hurts the performance of multimodal sentiment analysis models directly. To address this problem, we propose the sentiment word aware multimodal refinement model (SWRM), which can dynamically refine the erroneous sentiment words by leveraging multimodal sentiment clues. Specifically, we first use the sentiment word position detection module to obtain the most possible position of the sentiment word in the text and then utilize the multimodal sentiment word refinement module to dynamically refine the sentiment word embeddings. The refined embeddings are taken as the textual inputs of the multimodal feature fusion module to predict the sentiment labels. We conduct extensive experiments on the real-world datasets including MOSI-Speechbrain, MOSI-IBM, and MOSI-iFlytek and the results demonstrate the effectiveness of our model, which surpasses the current state-of-the-art models on three datasets. Furthermore, our approach can be adapted for other multimodal feature fusion models easily 1 .

Wenting Zhao, Konstantine Arkoudas, Weiqi Sun, Claire Cardie. Proceedings of the 2022 Conference of the North American Chapter of the Association for Computational Linguistics: Human Language Technologies. 2022.