Muhammad Qamar Raza

A Comparative Analysis of Neural Network Based Short Term Load Forecast Models for Anomalous Days Load Prediction

Load forecasting plays a very vital role for efficient and reliable operation of the power system. Often uncertainties significantly decrease the prediction accuracy of load forecasting which affect the operational cost dramatically. In this paper, comparison of Back Propagation (BP) and Levenberg Marquardt (LM) neural network (NN) forecast model for 24 hours ahead is presented. The impact of lagged load data, calendar events and weather variables on load demand are analyzed in order to select the best forecast model inputs. The mean absolute percentage errors (MAPE), Daily peak error and regression analysis of NN training are used to measure the NN performance. The Forecast results demonstrate that, LM based forecast model outperform than BP NN model for performance matrices. This model is used to predict the load of ISO-New England grid. Index Terms—Short Term Load Forecasting (STLF), Neural Network (NN), Back Propagation (BP), Levenberg- Marquardt (LM), Mean Absolute Percentage Error (MAPE), Regression Analysis (RA).

An improved neural ensemble framework for accurate PV output power forecast

A significant role of renewable energy resource such as solar photovoltaic (PV) is substantially important for the smart grid. One of a major challenge for large scale integration of PV into the grid is intermittent and uncertain nature of solar PV. Therefore, developing a framework for accurate PV output power forecast is utmost important. In this research, a novel ensemble forecast framework is purposed. A novel feed forward neural network (FNN) ensemble based forecast framework is proposed and trained with particle swarm optimization (PSO). The wavelet transform (WT) technique is applied to handle the sharp spikes and fluctuations in historical PV output data. Correlated variables such as PV output power data, solar irradiance, temperature, humidity and wind speed are applied as inputs to forecast the PV output power precisely. The performance of proposed framework was analyzed for one day ahead load PV output power forecast of summer (S), autumn (A), winter (W) and spring (SP) days. The selected days from each season are a clear day (CD), partial cloudy day (PCD) and cloudy day (CLD). The proposed forecast framework provides higher forecast accuracy compared to persistence and backpropagation neural network (BPNN) model.

Adaptive neural network based backstepping control design for MIMO nonlinear systems with actuator nonlinearities

Purpose – The purpose of the proposed research methodology is to control the trajectory tracking of EDRM and also to cancel out the effect of no-smooth nonlinearities, which affect the system performance badly. Design/methodology/approach – Robust adaptive neural network (RANN)-based backstepping control design methodology is presented in this paper. The proposed design methodology improves the trajectory tracking and running mean error. Findings – The running mean error results show that the convergence of the proposed RANN-based backstepping technique is very fast as compare to the conventional PD control and due to this proposed control technique, the EDRM follows its desired trajectory perfectly. Practical implications – The EDRM trajectory tracking performance increases which leads to a better working position of EDRM. Originality/value – The originality of this research article is 93 per cent.

Backstepping control using adaptive neural network for industrial two link robot manipulator

This paper highlights, neural network (NN) based adaptive control using backstepping control technique is proposed for robot manipulator trajectory tracking. Firstly, the vector of current is considered as the control variable for robot manipulator mechanical subsystem by using the adaptive update algorithm of NN and an enclosed control input for the desired vector of current is constructed. So that, the goal of trajectory tracking of robot manipulator is achieved. Secondly, the voltage commands are constructed in order to control the joint currents to follow the anticipated value by using the NN controller in order to manipulate the dynamics of DC motor. Simplicity of control law is achieved by using proposed control technique along with low computational cost. In addition, robot manipulator and its actuator dynamics does not require the mathematical representation of model. The weight values of NNs and robotic manipulator parameters are adaptively updated. The efficiency and usefulness of proposed scheme on 2-DOF robot manipulator is analyzed by using the running mean error. The results depicts that the proposed model out perform than the conventional PD controller in terms of enhanced robotic manipulator trajectory tracking.

A multivariate ensemble framework for short term solar photovoltaic output power forecast

In emerging renewable energy resources, solar photovoltaic (PV) is substantially important to fulfil the future electricity demand. One of the major challenges for large scale integration of PV into the grid is intermittent and uncertain nature of its output. Therefore, it is utmost important to forecast the solar PV output power with higher accuracy. In this paper, a novel ensemble forecast framework is proposed based on autoregressive (AR), radial basis function (RBF) and forward neural network (FNN) predictors. The neural predictor (FNN and RBF) are trained with particle swarm optimization (PSO) to enhance the prediction performance. Furthermore, wavelet transform (WT) technique is applied to remove the sharp spikes and fluctuations in it. In addition, correlated variables such as PV output power data, solar irradiance, temperature, humidity and wind speed are applied as inputs to multivariate ensemble network. The performance of proposed framework is analyzed for one day and week ahead case studies. The selected days from each season are a clear day (CD), partial cloudy day (PCD) and cloudy day (CLD). The proposed forecast framework provides a reduction in forecast nRMSE in seasonal daily and week ahead case studies.