Climate, Energy and Water Research Institute (CEWRI), National Agricultural Research Centre (NARC) Pakistan Agricultural Research Council Islamabad Pakistan
Auto-generated profile, based on publicly available information
Ghani Akbar
Climate, Energy and Water Research Institute (CEWRI), National Agricultural Research Centre (NARC) Pakistan Agricultural Research Council Islamabad Pakistan
Enhancement of the dispatching capacity and efficiency of grid management requires knowledge of photovoltaic power generation beforehand. Intrinsically, photovoltaic power generation is highly volatile and irregular, which impedes its prediction accuracy. In order to handle these constraints, this paper proposes deep learning-based approaches and a pre-processing algorithm. The proposed scheme employs Pearson’s Correlation Coefficient to find the similarity between atmospheric variables and PV power generation. Based on high PCC values, top atmospheric variables, and PV power generated time series data are passed through the Empirical Mode Decomposition (EMD) to simplify the complex data streams into Intrinsic Mode Functions (IMFs). Further, to streamline the prediction process, the proposed correlation-based signal synthesis (CBSS) algorithm finds combinations of these IMFs, which have a high correlation value between atmospheric variables and PV power data. Deep learning models of algorithms Long Short Term Memory (LSTM) and Nonlinear Autoregressive Network with Exogenous Inputs (NARX) network with the configurations of three networks, a single network, and the direct approach employed for the prediction of IMFs combinations. LSTM network was analyzed under the Adaptive moment estimation (ADAM), Stochastic Gradient Descent with Momentum (SGDM), and Root Mean Square Propagation (RMSP) optimization. Extensive experimentation was evaluated using atmospheric data collected at the Climate, Energy, and Water Research Institute (CEWRI), NARC, Islamabad, Pakistan. RMSE, MAE, MAPE, and R 2 performance measures show promising prediction results for the LSTM under the configuration of three networks and ADAM optimization.
| The suboptimal irrigation management on small raised beds farms in the Indus Basin is considered to reduce irrigation efficiency and exacerbates waterlogging and salinity. Addressing this issue, farmer managed irrigations on commonly used Narrow Bed (NB) with furrow spacings 66 cm and newly introduced Wide Bed (WB) with furrow spacing 130 cm on sandy clay loam, were investigated using the irrigation modelling software, WinSRFR, to explore irrigation management strategies for improving irrigation eficiency. The study revealed existing average application efficiency of low quarter ( AE lq ) 71%, 87%, distribution uniformity of low quarter ( DU lq ) 70%, 80% and adequacy of low quarter ( AD lq ) 100 %, 90% for NB and WB, respectively. Majority (67%) of WB irrigations monitored were under irrigated while large number (50%) of NB irrigation were over irrigated. Simulation modelling showed that achievement of above 90% Potential Application Efficiency (PAE) is possible by improving operation (inflow rate and time to irrigation cut-off) and field design (field length and width/number of furrows per set). This work raised the prospects of improved irrigation efficiency of raised beds in Indus Basin, which may be possible without incurring any costs associated with altered infrastructure, new or modified machinery, or increased labour.