A renewable energy forecasting and control approach to secured edge-level efficiency in a distributed micro-grid

Abstract

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.

A Bibliometric Analysis of Solar Energy Forecasting Studies in Africa

“…According to the analysis of the keywords in Figure 5, the red cluster had dominant keywords indicating the high frequency of occurrence, implying that most researchers in solar energy forecasting in Africa were interested in "weather forecasting" appearing in 71 articles, "numerical models" (56), "satellite imagery" (41), "computer simulations" (40) and "parameterization" (35). This is not surprising because some of the recent studies [15,29,35] conducted in Africa have developed different methods for solar irradiance forecasting such as statistical approaches using historical data, the use of NWP models, tracking cloud movement from satellite images and tracking cloud movements from direct ground observations using sky cameras (more notable methods and reviews on solar energy forecasting models are discussed in Mpfumali et al [14]).…”

“…Globally, renewable energy forecasting is gaining more traction in the research field due to inherent socio-economic benefits for society and the environment. In addition to the role played by renewable energy in the mitigation of greenhouse gas emissions, renewable energy forecasting assists in conserving energy for future use, particularly where storage systems are incorporated into the energy systems [40]. In Africa, the growth in energy demand has been noted and is currently fulfilled via centralized and conventional power generators and fossil fuel-based generations [31].…”

“…This cluster reflects on different themes that address important aspects of forecasting. The most frequently occurring keywords in the red cluster are "weather forecasting" appearing in 71 articles, "numerical models" (56), "satellite imagery" (41), "computer simulations" (40), and "parameterization" (35) for Africa. Meanwhile, much attention in southern Africa was given to words such as "evapotranspiration", "regional climate", "global warming", "satellite imagery", "machine learning", and remote sensing"; these appeared in 43, 38, 36, 29, 25 and 24 articles, respectively.…”

“…Meanwhile, much attention in southern Africa was given to words such as "evapotranspiration", "regional climate", "global warming", "satellite imagery", "machine learning", and remote sensing"; these appeared in 43, 38, 36, 29, 25 and 24 articles, respectively. Weather forecasting (71); numerical models (56); satellite imagery (41); computer simulations (40); parameterization (35) Red ( 21) Evapotranspiration (43); Regional climate (38); global warming (36); satellite imagery (29); machine learning (25); remote sensing (24) Green (21) Climate change (52); drought (43); remote sensing (33); agriculture (27) Green (20) Weather forecasting (33); precipitation (29); wind (29); drought (24); sea surface temperature (22) Blue ( 14) Forecasting (71); Solar energy (62); solar power generation (30); wind power (24); energy policy (15) Blue ( 12) Africa ( 53); solar radiation (24); solar energy (22); radiation (18) Yellow ( 12) Solar radiation (88); prediction (44); temperature (39); Simulation (32) Yellow ( 4) Forecasting (21); ecosystem (11) Purple ( 10) Africa (88); mathematical models (55); atmospheric humidity (34); radiation (32); Purple (3) Climate change (43); climate prediction…”

A Unique Three-Step Weather Data Approach in Solar Energy Prediction Using Machine Learning

“…With regards to data type, some studies pair the solar energy produced from solar panels with either exclusively historically observed data [8][9][10][11][12][13][14][15][16][17][18] or forecast data [19][20][21][22]. Others use only the historical PV output data [23,24]. Recall that the on-site weather station can capture local conditions that affect the weather that are not reflected in local or regional weather data.…”