Reinforcement Learning Approaches to Power System Scheduling

One major component of power system operation is generation scheduling. The objective of the work is to develop efficient control strategies to the power scheduling problems through Reinforcement Learning approaches. The three important active power scheduling problems are Unit Commitment, Economic Dispatch and Automatic Generation Control. Numerical solution methods proposed for solution of power scheduling are insufficient in handling large and complex systems. Soft Computing methods like Simulated Annealing, Evolutionary Programming etc., are efficient in handling complex cost functions, but find limitation in handling stochastic data existing in a practical system. Also the learning steps are to be repeated for each load demand which increases the computation time.Reinforcement Learning (RL) is a method of learning through interactions with environment. The main advantage of this approach is it does not require a precise mathematical formulation. It can learn either by interacting with the environment or interacting with a simulation model. Several optimization and control problems have been solved through Reinforcement Learning approach. The application of Reinforcement Learning in the field of Power system has been a few. The objective is to introduce and extend Reinforcement Learning approaches for the active power scheduling problems in an implementable manner. The main objectives can be enumerated as:(i) Evolve Reinforcement Learning based solutions to the Unit Commitment Problem.(ii) Find suitable solution strategies through Reinforcement Learning approach for Economic Dispatch. (iii) Extend the Reinforcement Learning solution to Automatic Generation Control with a different perspective. (iv) Check the suitability of the scheduling solutions to one of the existing power systems.First part of the thesis is concerned with the Reinforcement Learning approach to Unit Commitment problem. Unit Commitment Problem is formulated as a multi stage decision process. Q learning solution is developed to obtain the optimwn commitment schedule. Method of state aggregation is used to formulate an efficient solution considering the minimwn up time I down time constraints. The performance of the algorithms are evaluated for different systems and compared with other stochastic methods like Genetic Algorithm.Second stage of the work is concerned with solving Economic Dispatch problem. A simple and straight forward decision making strategy is first proposed in the Learning Automata algorithm. Then to solve the scheduling task of systems with large number of generating units, the problem is formulated as a multi stage decision making task. The solution obtained is extended in order to incorporate the transmission losses in the system. To make the Reinforcement Learning solution more efficient and to handle continuous state space, a fimction approximation strategy is proposed. The performance of the developed algorithms are tested for several standard test cases. Proposed method is compared with other recent methods like Partition Approach Algorithm, Simulated Annealing etc.As the final step of implementing the active power control loops in power system, Automatic Generation Control is also taken into consideration.Reinforcement Learning has already been applied to solve Automatic Generation Control loop. The RL solution is extended to take up the approach of common frequency for all the interconnected areas, more similar to practical systems. Performance of the RL controller is also compared with that of the conventional integral controller.In order to prove the suitability of the proposed methods to practical systems, second plant ofNeyveli Thennal Power Station (NTPS IT) is taken for case study. The perfonnance of the Reinforcement Learning solution is found to be better than the other existing methods, which provide the promising step towards RL based control schemes for practical power industry.Reinforcement Learning is applied to solve the scheduling problems in the power industry and found to give satisfactory perfonnance. Proposed solution provides a scope for getting more profit as the economic schedule is obtained instantaneously. Since Reinforcement Learning method can take the stochastic cost data obtained time to time from a plant, it gives an implementable method. As a further step, with suitable methods to interface with on line data, economic scheduling can be achieved instantaneously in a generation control center. Also power scheduling of systems with different sources such as hydro, thermal etc. can be looked into and Reinforcement Learning solutions can be achieved.

A marine candida sake as source of immunostimulants to fenneropenaeus indicus

Aquaculture has developed rapidly over the last three decades to become an important activity worldwide.The Food and Agricultural Organization (FAO) of the UN acknowledge that global fishery output must be increased by at least 50% to offset projected shortfalls in dietary protein by 2030.LAquaculture has developed rapidly over the last three decades and has become an importat industry as today’s demand for fish exceeds the natural supply.lmmunostimulants are chemical compounds that activate the immune system of animals and render them more resistant to infections by viruses, bacteria, fungi, and parasites. lmmunostimulants have been obtained from diverse natural sources where, microbial cell wall acts as the main source.The salient findings of the study are summariseSeven marine yeasts were screened for growth promoting and immunostimulant property in F. indicus. Candida sake S165 was found to be best in terms of its support for growth and protection against white spot virus infection.The study revealed that marine yeast Candida sake can be effectively used as potential source of immunostimulants for application in penaeid prawns culture systems. The study emphasise the fact that the dose and frequency of application of immunostimulants are to be standardised and validated before commercialisation to achieve optimum stimulation of the immune system and to avoid immune fatigue die to verdose.Marine yeast (whole cell) was found to support better immunostimulation compared to its cell wall component B-1,3-glucan. This study shows that administration of marine yeast (whole cell) or B-1,3-glucan as immunostimulants in aquaculture would definitely help in protection of the stock to a few more days even though total protection is not being imparted. This partial protection itself would be highly helpful to the farming industry so that they can get sufficient time to plan for a safe harvest and save the crop from cent percent mortality.

Compensation to Workmen for Industrial Injuries

This thesis Entitled compensation to workmen for industrial injuries.Evaluation of the different forms of liability for compensating industrial injuries makes it evident that the liability under the social insurance scheme is the most befitting one, as it eliminates the problem of evasion of liability by the employer by providing for sharing of liability. Liability for compensation under the workmen's Compensation Act, 1923 and the Employees' State Insurance Act, 1948 arises only in the case of accidents, arising in the course of and out of employment. Majority of the workers, covered by the workmen's Compensation Act, have supported lumpsum payment of compensation under the Act. It appears that workers are ignorant of the cemerits of lumpsum payment. So, the workers should be properly educated by the Inspectorate, proposed above, about the comparative advantages of periodical payments. It is suggested that the workmens Compensation Act, 1923 may be amended, imposing fee upon the parties for each adjournment. It is also suggested that provision may be made in the workmens Compensation Act, 1923 for the expeditious despatch of amendments of the Workmen's Compensation Act, 1923, the Workmens· Compensation Rules, 1924 and the Schedules, made from time to time, to the comrnissioners for workmens Compensation, This will help them mete out justice to an injured workman, as required by the changes in the law. The Employees' State Insurance Act, 1948 and the Rules may be amended, requiring the employers to provide the employees with necessary information, in the vernacular language, about the employment injury benefits available under the Employees' State Insurance Act, 1948 and the formalities for obtaining the same. This will help the illiterate employees, especially the casual ones, avail of employment injury benefits. Changes in the law, on the lines suggested above, are imperative to make the system of compensation for industrial injuries prove effective and beneficial to injured workmen.

Behaviour of laterised normal and self compacting concrete subjected to elevated temperatures

Concrete is a universal material in the construction industry. With natural resources like sand and aggregate, fast depleting, it is time to look for alternate materials to substitute these in the process of making concrete. There are instances like exposure to solar radiation, fire, furnaces, and nuclear reactor vessels, special applications like missile launching pads etc., where concrete is exposed to temperature variations In this research work, an attempt has been made to understand the behaviour of concrete when weathered laterite aggregate is used in both conventional and self compacting normal strength concrete. The study has been extended to understand the thermal behaviour of both types of laterised concretes and to check suitability as a fire protection material. A systematic study of laterised concrete considering parameters like source of laterite aggregate, grades of Ordinary Portland Cement (OPC) and types of supplementary cementitious materials (fly ash and GGBFS) has been carried out to arrive at a feasible combination of various ingredients in laterised concrete. A mix design methodology has been proposed for making normal strength laterised self compacting concrete based on trial mixes and the same has also been validated. The physical and mechanical properties of laterised concretes have been studied with respect to different variables like exposure temperature (200°C, 400°C and 600°C) and cooling environment (air cooled and water cooled). The behaviour of ferrocement elements with laterised self compacting concrete has also been studied by varying the cover to mesh reinforcement (10mm to 50mm at an interval of 10mm), exposure temperature and cooling environment.

An Effective Path Protection Method to Attain the Route Stability in MANET

With the increasing popularity of wireless network and its application, mobile ad-hoc networks (MANETS) emerged recently. MANET topology is highly dynamic in nature and nodes are highly mobile so that the rate of link failure is more in MANET. There is no central control over the nodes and the control is distributed among nodes and they can act as either router or source. MANTEs have been considered as isolated stand-alone network. Node can add or remove at any time and it is not infrastructure dependent. So at any time at any where the network can setup and a trouble free communication is possible. Due to more chances of link failures, collisions and transmission errors in MANET, the maintenance of network became costly. As per the study more frequent link failures became an important aspect of diminishing the performance of the network and also it is not predictable. The main objective of this paper is to study the route instability in AODV protocol and suggest a solution for improvement. This paper proposes a new approach to reduce the route failure by storing the alternate route in the intermediate nodes. In this algorithm intermediate nodes are also involved in the route discovery process. This reduces the route establishment overhead as well as the time to find the reroute when a link failure occurs.

How to do a dissertation

The role of the supervisor• agree a timetable of meetings at the start of your project and stick to it;• make sure that each meeting has a focus eg “setting a research problem”,“analysing the data”;• send something that can form the basis of a discussion about your progress to your supervisor before each meeting. This could include your research plan, early results of your data collection or draft chapters;• turn up on time to each meeting you have arranged. Do not assume that your supervisor is available at all times to see you;• at the end of each

On Queueinginventory Models – product form solution; reservation, Cancellation and common life time

Queueing theory is the mathematical study of ‘queue’ or ‘waiting lines’ where an item from inventory is provided to the customer on completion of service. A typical queueing system consists of a queue and a server. Customers arrive in the system from outside and join the queue in a certain way. The server picks up customers and serves them according to certain service discipline. Customers leave the system immediately after their service is completed. For queueing systems, queue length, waiting time and busy period are of primary interest to applications. The theory permits the derivation and calculation of several performance measures including the average waiting time in the queue or the system, mean queue length, traffic intensity, the expected number waiting or receiving service, mean busy period, distribution of queue length, and the probability of encountering the system in certain states, such as empty, full, having an available server or having to wait a certain time to be served.