Energy forecasting using Renewable energy sources (RESs) is gradually gaining weight in the research field due to the benefits it presents to the modern-day environment. Not only does energy forecasting using renewable energy sources help mitigate the greenhouse effect, it also helps to conserve energy for future use. Over the years, several methods for energy forecasting have been proposed, all of which were more concerned with the accuracy of the prediction models with little or no considerations to the operating environment. This research, however, proposes the uses of Deep Neural Network (DNN) for energy forecasting on mobile devices at the edge of the network. This ensures low latency and communication overhead for all energy forecasting operations since they are carried out at the network periphery. Nevertheless, the cloud would be used as a support for the mobile devices by providing permanent storage for the locally generated data and a platform for offloading resource-intensive computations that exceed the capabilities of the local mobile devices as well as security for them. Electrical network topology was proposed which allows seamless incorporation of multiple RESs into the distributed renewable energy source (D-RES) network. Moreover, a novel grid control algorithm that uses the forecasting model to administer a well-coordinated and effective control for renewable energy sources (RESs) in the electrical network is designed. The electrical network was simulated with two RESs and a DNN model was used to create a forecasting model for the simulated network. The model was trained using a dataset from a solar power generation company in Belgium (elis) and was experimented with a different number of layers to determine the optimum architecture for performing the forecasting operations. The performance of each architecture was evaluated using the mean square error (MSE) and the r-square.
This study evaluated the historical precipitation simulations of 49 global climate models (GCMs) of the Coupled Model Intercomparison Project Phase 6 (CMIP6) in reproducing annual and seasonal precipitation climatology, linear trends, and their spatial correlation with global SST across Africa and the Arabian Peninsula during the period of 1980–2014, using Global Precipitation Climatology Centre (GPCP) data as a reference. Taylor’s diagram was used to quantify the strengths and weaknesses of the models in simulating precipitation. The CMIP6 multi-mean ensemble (MME) and the majority of the GCMs replicated the dominant features of the spatial and temporal variations reasonably well. The CMIP6 MME outperformed the majority of the individual models. The spatial variation of the CMIP6 MME closely matched the observation. The results showed that at annual and seasonal scales, the GPCP and CMIP6 MME reproduced a coherent spatial pattern in terms of the magnitude of precipitation. The humid region received >300 mm and the arid region received <50 mm across Africa and the Arabian Peninsula. The models from the same modeling centers replicated the precipitation levels across different seasons and regions. The CMIP6 MME and the majority of the individual models overestimate (underestimate) in humid (arid and semi-arid)-climate zones. The annual and pre-monsoon seasons (i.e., DJFMA) were better replicated in the CMIP6 GCMs than in the monsoon-precipitation model (MJJASON). The CMIP6 MME (GPCP) showed stronger wetting (drying) trends in the northern hemisphere. In contrast, a strong drying trend in the CMIP6 MME and a weak wetting trend in the GPCP were shown in the Southern Hemisphere. The CMIP6 MME captures the spatial pattern of linear trends better than individual models across different climate zones and regions. The relationship between precipitation and sea-surface temperature (SST) exhibited a high spatial correlation (−0.80 and 0.80) with large variability across different regions and climate zones. The GPCP (CMIP6 MME) exhibited a heterogenous (homogeneous) spatial pattern, with higher correlation coefficients recorded in the CMIP6 MME than in the GPCP in all cases. Individual models from the same modeling centers showed spatial homogeneity in correlation values. The differences exhibited by the individual GCMs highlight the significance of each model’s unique dynamics and physics; however, model selection should be considered for specific applications.
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.