Navneet Kumar Singh

A radial basis function neural network approach for multi-hour short term load-price forecasting with type of day parameter

In 1990s, after deregulation of Australian electricity market, electricity became a commodity that can be bought and sold. This led power industry to change their planning strategies. In this planning Short Term Load Forecasting (STLF) plays a vital role to provide unit commitment, economic generation scheduling etc. In this paper, RBF neural network (RBFNN) is applied as short term load as well as price forecaster. While modeling process, day-type (Sunday, Monday, etc.) is considered as an extra input to the neural network. The prediction performance of proposed RBFNN architecture is evaluated using Mean of Mean Absolute Percentage Error (MMAPE) between actual data and forecasted data of New South Wales (Australia). The results obtained are compared with the results gained from classical moving average (MA), Holt-Winters and Feed Forward Neural Network (FFNN) methods. It is, in general, observed that the RBFNN is more accurate and works better with inclusion of day type input parameters.

Demand side energy management in hybrid microgrid system using heuristic techniques

Fulfilling the energy demand is an important issue in the power system. As conventional fossil fuels based energy resources are limited on the earth and expected to be depleted in few decades. Microgrid with battery energy storage is commonly employed nowadays to full-fill the demand. For better performance of microgrid, optimal energy management is essential. Therefore, the optimal utilization of renewable energy resources (RES) is emphasized in this paper. Three different cases, i.e., without battery, with battery, and considering battery with its life cost are simulated and analyzed. By the results obtained, it is deduced that use of the battery is successful to incorporate extra power demand at a cost of very less profit reduction, i.e., due to the use of batteries. Various heuristic techniques, i.e. Particle Swarm Optimization (PSO), Firefly Algorithm (FA), and Artificial Bee Colony (ABC) are applied to establish the optimal operation of the wind, hydro and battery-based microgrid. A comparative study of these heuristic techniques shows that ABC provides promising results.

SELECTION OF HIDDEN LAYER NEURONS AND BEST TRAINING METHOD FOR FFNN IN APPLICATION OF LONG TERM LOAD FORECASTING

Selection of Hidden Layer Neurons and Best Training Method for FFNN in Application of Long Term Load Forecasting For power industries electricity load forecast plays an important role for real-time control, security, optimal unit commitment, economic scheduling, maintenance, energy management, and plant structure planning etc. A new technique for long term load forecasting (LTLF) using optimized feed forward artificial neural network (FFNN) architecture is presented in this paper, which selects optimal number of neurons in the hidden layer as well as the best training method for the case study. The prediction performance of proposed technique is evaluated using mean absolute percentage error (MAPE) of Thailand private electricity consumption and forecasted data. The results obtained are compared with the results of classical auto-regressive (AR) and moving average (MA) methods. It is, in general, observed that the proposed method is prediction wise more accurate.

A comparative study of BPNN, RBFNN and ELMAN neural network for short-term electric load forecasting: A case study of Delhi region

Constant tariff scheme produces a large and continuously-changing difference between electricity cost and price. Consequently, the concern of power system planning and economic generation becomes significant. To overcome this problem accurate load forecasting is a field of immense importance. Conventional methods, i.e., Moving Average (MA) and Holt-Winter (HW) methods are inappropriate to forecast in highly non-linear electrical environment, as existing in Delhi region. In this paper, electrical Load (L), Temperature (T), Relative Humidity (RH) and atmospheric Pressure (Pr) of New Delhi, India are analysed and used to develop the load forecasting model. This paper presents the results of an investigation on various Artificial Neural Networks (ANNs), i.e., Back Propagation Neural Network (BPNN), Radial Basis Function Neural Network (RBFNN) and ELMAN Neural Network (ELMNN), together with specified conventional methods, due to non-linear mapping characteristics of electrical load. Day-Type (D) is additionally used as an input parameter to improve the forecasting accuracy. The investigation has shown that the ELMNN is more accurate than other ANN structures and conventional methods.

PSO optimized radial basis function neural network based electric load forecasting model

Accurate and robust load forecasting models play an important role in power system planning. Due to smaller size and inherent property of good classification, Radial Basis Function Neural Network (RBFNN) is always preferred over other neural network structures. It is used by researchers as an effective tool for Short-Term Load Forecasting (STLF). The smaller size of this network may lead its output to be a local solution. To train RBFNN, fixing centre widths of hidden layer activation functions and the output layer weights are important. To solve this problem of trapping in local optima, a hybrid forecasting model, i.e., Particle Swarm Optimization (PSO) based RBFNN (PRBFNN) is proposed in this paper. In the proposed model centre widths and output layer weights are optimized by PSO. Therefore, the proposed model keeps the advantages of PSO, as well as RBFNN. The proposed model is tested on the hourly load data for New South Wales, Australia. The results obtained show that the accuracy of the proposed model, in terms of Mean of Mean Absolute Percentage Error (MMAPE) is better than existing artificial neural network based approaches, i.e., Feed Forward Neural Network, RBFNN and Elman Neural Network. The forecasting performance of proposed model, and classical models, i.e., Auto-regressive (AR) and Moving Average (MA), presented in a past research work, is also compared. Again, the performance of proposed model is found better.

Superconducting fault current limiter for grid connected power system protection

Now-a-days, superconducting fault current limiters are in general found increasing in land-based power systems due to the enhancement of the distribution system. To limit this current, up-gradation of expensive current limiting equipments is investigated by several researchers, and various fault current limiting techniques have been developed. Superconducting fault current limiter (SFCL) is used to reduce the effect of unforeseen disturbances within the grid in transmission and distribution system. In smart-grid trend, SFCL has proved itself to be most promising device. In this paper, SFCL is implemented in MATLAB/ SIMULINK environment for grid connected power system protection. A transient analysis is performed for 3-phase L-G faults at different locations of the grid. To validate the effectiveness of the device in the grid, transient analysis without SFCL, is performed. With this analysis optimal location for SFCL installation is identified. While analysis, multi-criteria formulation is considered and number of SFCL are installed within the grid for better protection. Amongst number of varieties of SFCL devices, used in power system, resistive type SFCL is discussed and analyzed in this paper. For simulation purpose, a wind farm with a capacity of 10 MVA is modeled. The methodology developed shows the optimal placement of the SFCL and results obtained ratify the application of SFCL.

Energy scheduling of Wind-Battery-Hydro based hybrid microgrid system using heuristic techniques

Recently, trends towards the integration of renewable energy sources (RES) like wind energy in to the microgrid increased sharply, so the requirement of battery storage system (BSS) also increased dramatically to make these sources dispatchable. Optimal scheduling of renewable energies along with BSS is a tedious task, as these sources are dependent on uncertainty of nature. In this paper various heuristic techniques like particle swarm optimization (PSO) and its variants, and firefly algorithm (FA) are tested for optimal scheduling of Wind-Battery-Hydro based hybrid microgrid system. The proposed problem maximizes net profit of microgrid while accommodating uncertainty of wind power. MATLAB® platform is used to perform the simulation. Simulation results show the effectiveness of FA. It provides best profit for optimal energy scheduling in microgrid as compared to other techniques.

Superconducting Fault Current Limiter for Grid Connected Power System Protection

Now-a-days, superconducting fault current limiters are in general found increasing in land-based power systems due to the enhancement of the distribution system. To limit this current, up-gradation of expensive current limiting equipments is investigated by several researchers, and various fault current limiting techniques have been developed. Superconducting fault current limiter (SFCL) is used to reduce the effect of unforeseen disturbances within the grid in transmission and distribution system. In smart-grid trend, SFCL has proved itself to be most promising device. In this paper, SFCL is implemented in MATLAB/ SIMULINK environment for grid connected power system protection. A transient analysis is performed for 3-phase L-G faults at different locations of the grid. To validate the effectiveness of the device in the grid, transient analysis without SFCL, is performed. With this analysis optimal location for SFCL installation is identified. While analysis, multi-criteria formulation is considered and number of SFCL are installed within the grid for better protection. Amongst number of varieties of SFCL devices, used in power system, resistive type SFCL is discussed and analyzed in this paper. For simulation purpose, a wind farm with a capacity of 10 MVA is modeled. The methodology developed shows the optimal placement of the SFCL and results obtained ratify the application of SFCL.

Optimal energy management of hybrid power system with two different battery models

Now a days, wind and solar energy are most commonly used as renewable energy sources (RES). These sources highly depend on environment and geographical conditions of a particular location. Main drawback of RES is randomness in power production due to their inherent uncertainty nature. Hence, energy management is difficult task for these sources. Wind, photovoltaic (PV) and sodium nickel chloride (SNC) battery based hybrid power system (HPS) is used as study system in this paper. Two battery models, i.e., internal resistance (IR) and two time constant (TTC) model are modeled. System operation is carried in two stages for these two battery model separately, in first stage voltage of system is maintained at constant value using voltage source converter (VSC) after that in second stage dynamic programming (DP) is applied to system to get maximum revenue from the system.

Gross Ton-Kilometer forecasting models for freight trains of Northern-Central Indian railways

Indian Railways (IR) earns about 70% of its revenue from freight traffic. The goods loading is highly erratic in nature which creates the problem of inaccurate forecasting of the electric power required. Thus, IR requires precise forecasting models to deal with this problem. In this paper, Gross Ton KiloMeter (GTKM) earned by freight traffic is forecasted using traditional statistical models, i.e., exponential smoothing, moving averages, weighted moving averages, trend corrected exponential smoothing (Holts method) and Holt-Winters (HW) approach, with proper experimentation. Real time GTKM data of a common type of goods train, viz., BCN, BOXN, etc is considered for experimentation. The data is observed to be highly nonlinear in nature. Proposed HW model provides impressive forecasting results with a satisfactory figure of MAPE as 8.63%.