Variation in solar irradiance causes power generation fluctuations in solar power plants. Power grid operators need accurate irradiance forecasts to manage this variability. Many factors affect irradiance, including the time of year, weather and time of day. Cloud cover is one of the most important variables that affects solar power generation, but is also characterized by a high degree of variability and uncertainty. Deep learning methods have the ability to learn long-term dependencies within sequential data. We investigate the application of Gated Recurrent Units (GRU) to forecast solar irradiance and present the results of applying multivariate GRU to forecast hourly solar irradiance in Phoenix, Arizona. We compare and evaluate the performance of GRU against Long Short-Term Memory (LSTM) using strictly historical solar irradiance data as well as the addition of exogenous weather variables and cloud cover data. Based on our results, we found that the addition of exogenous weather variables and cloud cover data in both GRU and LSTM significantly improved forecasting accuracy, performing better than univariate and statistical models.
Virtual field trip is a way of providing users with some knowledge and exposure of a facility without requiring them to physically visit the location. Due to the high computational costs that are necessary to produce virtual environments (VEs), the potential for photorealism is sacrificed. Often these three-dimensional (3D) modeled applications use an unrealistic VE and, therefore, do not provide a full depiction of real-world environments. Panoramas can be used to showcase complex scenarios that are difficult to model and are computationally expensive to view in virtual reality (VR). Utilizing 360° panoramas can provide a low-cost and quick-to-capture alternative with photorealistic representations of the actual environment. The advantages of photorealism over 3D models for training and education are not clearly defined. This paper initially summarizes the development of a VR training application and initial pilot study. Quantitative and qualitative study then was conducted to compare the effectiveness of a 360° panorama VR training application and a 3D modeled one. Switching to a mobile VR headset saves money, increases mobility, decreases set-up and breakdown time, and has less spatial requirements. Testing results of the 3D modeled VE group had an average normalized gain of 0.03 and the 360° panorama group, 0.43. Although the 3D modeled group had slightly higher realism according to the presence questionnaire and had slightly higher averages in the comparative analysis questionnaire, the 360° panorama application has shown to be the most effective for training and the quickest to develop.
The optimal power flow (OPF) module optimizes the generation, transmission, and distribution of electric power without disrupting network power flow, operating limits, or constraints. Similarly to any power flow analysis technique, OPF also allows the determination of system’s state of operation, that is, the injected power, current, and voltage throughout the electric power system. In this context, there is a large range of OPF problems and different approaches to solve them. Moreover, the nature of OPF is evolving due to renewable energy integration and recent flexibility in power grids. This paper presents an original hybrid imperialist competitive and grey wolf algorithm (HIC-GWA) to solve twelve different study cases of simple and multiobjective OPF problems for modern power systems, including wind and photovoltaic power generators. The performance capabilities and potential of the proposed metaheuristic are presented, illustrating the applicability of the approach, and analyzed on two test systems: the IEEE 30 bus and IEEE 118 bus power systems. Sensitivity analysis has been performed on this approach to prove the robustness of the method. Obtained results are analyzed and compared with recently published OPF solutions. The proposed metaheuristic is more efficient and provides much better optimal solutions.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.