Long-term multivariate time series plays a significant role in many application areas such as power systems, trading, etc. However, their accurate prediction is quite difficult for conventional forecasting methods as they often exhibit high dimensionality and complex relationships. Recent works show that transformer-based approaches are quite effective for long-term forecasting thanks to their attention mechanism. However, in the presence of complex high-dimensional inputs, they show evidence of oversmoothing, limited capacity, and opacity. To this end, this paper introduces SETTer, a transformer-based model that addresses these challenges by incorporating novel techniques for decoupled self-attention and hybrid masking. The proposed techniques enable SETTer to effectively capture the dominant short- and long-term patterns across the temporal and channel dimensions. In addition, we enrich the model layers with simple explainable structures that indicate the discriminative pattern of SETTer. We show that with a single-layer transformer architecture, SETTer can effectively model long-term dependencies in the presence of varying data complexities. Extensive experiments on real-word benchmark datasets for long-term multivariate time series forecasting demonstrate that SETTer outperforms state-of-the-art models in 88% of the scenarios.
Abraham Ezema, C. Eze, F. Ponci et al.· 0 citations
This paper presents the development of an energy management system (EMS) designed for a commercial building microgrid that integrates both AC and DC grids. The building infrastructure includes various electrical loads, photovoltaic (PV) panels, and a battery energy storage system. Additionally, the facility is equipped with seven electric vehicle (EV) chargers, including five AC chargers and two DC chargers, with one of the DC chargers supporting bidirectional power flow. The primary objective of the EMS is to minimize overall energy costs incurred from purchasing electricity in the day-ahead market by optimizing the operation of these components. Several use cases are developed and evaluated, including a reference case and comparisons with baseline charging and rule-based EMS strategies. Additional analyses examine deviations in PV, load, and electricity-price forecasts; variations in user behavior and satisfaction requirements; different peak-shaving limits and penalty factors; alternative system operating modes; and increased PV and battery storage capacities. The evaluation of these use cases provides a detailed analysis of their impact on energy costs, consumption, and operational efficiency. The findings confirm that the EMS effectively optimizes power flow under diverse operating conditions in a commercial building environment.
F. Sohrabi, Aytug Yavuzer, Sergio Orlando et al.· IEEE Access· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
