Solar irradiance forecasting is an inevitable and most significant process in grid-connected photovoltaic systems. Solar power is highly non-linear, and thus to manage the grid operation efficiently, with irradiance forecasting for various timescales, such as an hour ahead, a day ahead, and a week ahead, strategies are developed and analysed in this article. However, the single time scale model can perform better for that specific time scale but cannot be employed for other time scale forecasting. Moreover, the data consideration for single time scale forecasting is limited. In this work, a multi-time scale model for solar irradiance forecasting is proposed based on the multi-task learning algorithm. An effective resource sharing scheme between each task is presented. The proposed multi-task learning algorithm is implemented with a long short-term memory (LSTM) neural network model and the performance is investigated for various time scale forecasting. The hyperparameter estimation of the proposed LSTM model is made by a hybrid chicken swarm optimizer based on combining the best features of both the chicken swarm optimization algorithm (CSO) and grey wolf optimization (GWO) algorithm. The proposed model is validated, comparing existing methodologies for single timescale forecasting, and the proposed strategy demonstrated highly consistent performance for all time scale forecasting with improved metric results.
In this work, the solar water collector flow tube geometry is modified as curved and spiral to enhance the system’s performance. The investigation is carried out experimentally under the meteorological conditions of the Kovilpatti region (9°10 ′ 0 ″ N, 77°52 ′ 0 ″ E), Tamil Nadu, India. The flow pipes of the solar water heater are made of copper material which has higher thermal conductivity to recover the water heat as thermal energy. The influence of the mass flow rate (MF) on the flow pipes with respect to the surface temperature for various configurations of the flow tubes is investigated. The two MFs of 0.0045 kg/s and 0.006 kg/s are tested. The MF of 0.006 kg/s yields the maximum efficiency of 73% compared to the other MF. The straight, curved, and spiral tubes yielded the maximum efficiency of 58%, 62%, and 69%, respectively, at 0.0045 kg/s. Similarly, the MF of 0.006 kg/s obtained an efficiency of 62%, 65%, and 73% for straight, curved, and spiral flow tubes, respectively. The economics and exergy of the system are analyzed. The maximum exergy efficiency of the collector is estimated to be 32% for the MF of 0.0045 kg/s for the spiral flow collector, and for the 0.006 kg/s MF, the obtained exergy efficiency is 27% for the spiral flow water heater. The economic analysis revealed that the expense is $0.0608 and $0.0512 worth of hot water produced for the domestic space heating.
The Agri-voltaic (AV) is an emerging technology to harness the solar energy. The performance of the AV modules depends on the incident solar radiation, geographical location and the surface temperature of the modules. The performance of the AV system needs to be monitored by manually or embedded controllers. The commercially available technologies for monitoring the system is costlier and need to be optimised. The Arduino controller is used to monitor the performance of the photovoltaic (PV) system in Coimbatore (11.0160 N, 76.95580 E), Tamilnadu, India. The PV surface temperature is monitored and controlled by flowing the water above the module by setting the mean ambient temperature as a reference temperature 34 °C when the system exceeds the reference temperature. PV surface temperature is reduced up to 16°C thus improved the electrical efficiency by 17% compare to the reference module. The Arduino controller control the relay to switch on the motor to control the mass flow rate of the water at 0.0028kg/s. The various parameters are measured such as voltage, current and solar radiation of the location and analysed. The estimated cost of monitoring system and various sensor is 10$ which cost comparatively 50% lower than the other PV monitoring controllers. This method can be employed in the medium and large-scale irrigation system.
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.
hi@scite.ai
10624 S. Eastern Ave., Ste. A-614
Henderson, NV 89052, USA
Copyright © 2024 scite LLC. All rights reserved.
Made with 💙 for researchers
Part of the Research Solutions Family.