A Reinforcement Learning Approach to Economic Dispatch using Neural Networks

This paper presents a Reinforcement Learning (RL) approach to economic dispatch (ED) using Radial Basis Function neural network. We formulate the ED as an N stage decision making problem. We propose a novel architecture to store Qvalues and present a learning algorithm to learn the weights of the neural network. Even though many stochastic search techniques like simulated annealing, genetic algorithm and evolutionary programming have been applied to ED, they require searching for the optimal solution for each load demand. Also they find limitation in handling stochastic cost functions. In our approach once we learn the Q-values, we can find the dispatch for any load demand. We have recently proposed a RL approach to ED. In that approach, we could find only the optimum dispatch for a set of specified discrete values of power demand. The performance of the proposed algorithm is validated by taking IEEE 6 bus system, considering transmission losses

OPTIMAL UTILIZATION OF SERVICE FACILITY FOR A k-OUT-OF-n SYSTEM WITH REPAIR BY EXTENDING SERVICE TO EXTERNAL CUSTOMERS IN A RETRIAL QUEUE

In this paper, we study a k-out-of-n system with single server who provides service to external customers also. The system consists of two parts:(i) a main queue consisting of customers (failed components of the k-out-of-n system) and (ii) a pool (of finite capacity M) of external customers together with an orbit for external customers who find the pool full. An external customer who finds the pool full on arrival, joins the orbit with probability and with probability 1− leaves the system forever. An orbital customer, who finds the pool full, at an epoch of repeated attempt, returns to orbit with probability (< 1) and with probability 1 − leaves the system forever. We compute the steady state system size probability. Several performance measures are computed, numerical illustrations are provided.

Modification of Polyethylenes by Reactive Extrusion

The main aim of the study was to optimise the reactive extrusion conditions in the conventional modification processes of polyethylenes in a single screw extruder.The optimum conditions for peroxide crosslinking of low density polyethylene (LDPE), linear low density polyethylene (LLDPE) and their blend were determined in a torque rheometer. The actual reactive extrusion was performed in a laboratory single screw extruder using the optimum parameters. The influence of the coagent, triaUyl cyanurate (TAC), on the cross linking of low density polyethylene in the presence of peroxide was also investigated. The peroxide crosslinking was found to improve the mechanical properties and the thermal stability of the polyethylenes. The efficiency of crosslinking was found to be improved by the addition of coagent such as TAC.The optimum conditions for silane grafting viz temperature, shear rate, silane and DCP concentrations were determined on a torque rheometer in the case of LDPE, LLDPE and their blend. Silane grafting of LDPE in the presence of peroxide was performed with and without addition of water. Compounding of such mixtures in the melt at high temperatures caused decomposition of the peroxide and grafting of alkoxy silyl groups to the polyethylene chains.The optimum parameters for maleic anhydride modification of LDPE, LLDPE and their blend were determined. The grafting reaction was confinned by FTIR spectroscopy. Modification of polyethylenes with maleic anhydride in the presence of dicumyl peroxide was found to be useful in improving mechanical properties. The improvement was found to be mainly due to the grafting of carboxyl group and formation of crosslinks between the chains. The cross linking initiated improvements indicate extended property profiles and new application fields for polyethylenes.On the whole the study shows that the optimum conditions for modifying polyethylenes can be determined on a torque rheometer and actual modification can be performed in a single screw extruder by employing the optimum parameters for improved mechanical! thermal behaviour without seriously affecting their processing behaviour.

Reactive loaded microstrip leaky wave antenna for low cost beam steering applications

A novel fixed frequency beam scanning microstrip leaky wave antenna is reported. The beam scanning at fixed frequency is achieved by reactive loading. Simulation and measured results shows frequency scanability of 80° as well as fixed frequency beam steering of 68° over the −10 dB impedance band of 4.56–5.06 GHz.

Studies on the Solvent Dependence in the Reaction of a Few (Anthracen-9-yl)MethyLamines and Sulfanes with Reactive Acetylenes

The thesis entitled ‘Studies on the Solvent Dependence in the Reaction of a Few (Anthracen-9-yl)methylamines and Sulfanes with Reactive Acetylenes’ is divided into six chapters. ln Chapter l a general survey of electron transfer reactions, Diels-Alder reactions and Michael-type additions is presented. A detailed discussion on the synthesis of several (anthracen-9-yl)methylamines is presented in Chapter 2. In Chapter 3, results of preliminary photophysical studies on a few (anthracen-9yl) methylamines are compiled. A detailed discussion on extensive examination of dependence in the reaction of (anthracen-9-yl)methylamines with reactive acetylenes is presented Chapter 4. Details on the synthesis and reaction of a few (anthracen-9-yl)methylsulfanes with DMAD are described in Chapter 5.

A Reinforcement Learning Algorithm to Economic Dispatch Considering Transmission Losses

Reinforcement Learning (RL) refers to a class of learning algorithms in which learning system learns which action to take in different situations by using a scalar evaluation received from the environment on performing an action. RL has been successfully applied to many multi stage decision making problem (MDP) where in each stage the learning systems decides which action has to be taken. Economic Dispatch (ED) problem is an important scheduling problem in power systems, which decides the amount of generation to be allocated to each generating unit so that the total cost of generation is minimized without violating system constraints. In this paper we formulate economic dispatch problem as a multi stage decision making problem. In this paper, we also develop RL based algorithm to solve the ED problem. The performance of our algorithm is compared with other recent methods. The main advantage of our method is it can learn the schedule for all possible demands simultaneously.

Reinforcement Learning approaches to Economic Dispatch problem

This paper presents Reinforcement Learning (RL) approaches to Economic Dispatch problem. In this paper, formulation of Economic Dispatch as a multi stage decision making problem is carried out, then two variants of RL algorithms are presented. A third algorithm which takes into consideration the transmission losses is also explained. Efficiency and flexibility of the proposed algorithms are demonstrated through different representative systems: a three generator system with given generation cost table, IEEE 30 bus system with quadratic cost functions, 10 generator system having piecewise quadratic cost functions and a 20 generator system considering transmission losses. A comparison of the computation times of different algorithms is also carried out.

Short-Term Load Forecast Of A Low Loadfactor Power System For Optimization Of Merit Order Dispatch Using Adaptive Learning Algorithm

Short term load forecasting is one of the key inputs to optimize the management of power system. Almost 60-65% of revenue expenditure of a distribution company is against power purchase. Cost of power depends on source of power. Hence any optimization strategy involves optimization in scheduling power from various sources. As the scheduling involves many technical and commercial considerations and constraints, the efficiency in scheduling depends on the accuracy of load forecast. Load forecasting is a topic much visited in research world and a number of papers using different techniques are already presented. The accuracy of forecast for the purpose of merit order dispatch decisions depends on the extent of the permissible variation in generation limits. For a system with low load factor, the peak and the off peak trough are prominent and the forecast should be able to identify these points to more accuracy rather than minimizing the error in the energy content. In this paper an attempt is made to apply Artificial Neural Network (ANN) with supervised learning based approach to make short term load forecasting for a power system with comparatively low load factor. Such power systems are usual in tropical areas with concentrated rainy season for a considerable period of the year

Optimal Design of a Surface Mounted Permanent-Magnet BLDC Motor for Spacecraft Applications

This paper presents the optimal design of a surface mounted permanent-magnet (PM) Brushless direct-current (BLDC) motor meant for spacecraft applications. The spacecraft applications requires the choice of a motor with high torque density, minimum cogging torque, better positional stability and high torque to inertia ratio. Performance of two types of machine configurations viz Slotted PMBLDC and Slotless PMBLDC with Halbach array are compared with the help of analytical and finite element (FE) methods. It is found that unlike a Slotted PMBLDC motor, the Slotless type with Halbach array develops zero cogging torque without reduction in the developed torque. Moreover, the machine being coreless provides high torque to inertia ratio and zero magnetic stiction

Reactive pozzolanas from rice husk ash: An alternative to cement for rural housing

This paper discusses the properties of rice husk ash samples produced from different types of field ovens to compare the performance of the ovens and to identify the most feasible method to produce a reactive pozzolana as an alternative to cement for building applications requiring lower strengths. Different types of ashes are produced and long-term strength of rice husk ash pozzolanas with lime or cement is investigated to suggest a sustainable affordable option in rural building applications, especially for rural housing in Kerala, a southern state of India