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.

Photopyroelectric study of thermal properties and phase transitions in selected solids

This thesis presents in detail. the theoretical developments and calculations which are used for the simultaneous determination of thermal parameters, namely thermal diffusivity (a). thermal effusivity (e), thermal conductivity (K) and heat capacity (cr ) employing photopyroelectric technique. In our calculations. we have assumed that the pyroelectric detector is supported on a copper backing. so that there will be sufficient heat exchange between the heated pyroelectric detector and the backing so that the signal fluctuations are reduced to a minimum. Since the PPE signal depends on the properties of the detector that are also temperature dependent. a careful temperature calibration of the system need to be carried out. APPE cell has been fabricated for the measurements that can be used to measure the thermal properties of solid samples from ~ 90 K to ~ 350 K. The cell has been calibrated using standard samples and the accuracy of the technique is found to be of the order of± 1%.In this thesis, we have taken up work n photopyroelectric investigation of thermal parameters of ferroelectric crystals such as Glycine phosphite (NH3CH2COOH3P03), Triglycine sulfate and Thiourea as well as mixed valence perovskites samples such as Lead doped Lanthanum Manganate (Lal_xPb~Mn03) Calcium doped (Lal_xCaxMnOJ) and Nickel doped Lanthanum Stroncium Cobaltate (Lao~Sro5Ni,Col_x03).The three ferroelectric crystals are prepared by the slow evaporation technique and the mixed valence perovskites by solid state reaction technique.Mixed valence perovskites, with the general formula RI_xA~Mn03 (R = La. Nd or Pr and A = Ba, Ca, Sr or Pb) have been materials of intense experimental and theoretical studies over the past few years. These materials show . colossal magneloresis/ance' (CMR) in samples with 0.2 < x < 0.5 in such a doping region, resistivity exhibits a peak at T = T p' the metal - insulator transition temperature. The system exhibits metallic characteristics with d %T > Oabove Tp (wherep is the resistivity) and insulating characteristics with d % T < 0 above T p. Despite intensive investigations on the CMR phenomena and associated electrical properties. not much work has been done on the variation of thermal properties of these samples. We have been quite successful in finding out the nature of anomaly associated with thermal properties when the sample undergoes M-I transition.The ferroelectric crystal showing para-ferroelectric phase transitions - Glycine phosphite. Thiourea and Triglycine sulfate - are studied in detail in order to see how well the PPE technique enables one to measure the thermal parameters during phase transitions. It is seen that the phase transition gets clearly reflected in the variation of thermal parameters. The anisotropy in thermal transport along different crystallographic directions are explained in terms of the elastic anisotropy and lattice contribution to the thermal conductivity. Interesting new results have been obtained on the above samples and are presented in three different chapters of the thesis.In summary. we have carried investigations of the variations of the thermal parameters during phase transitions employing photopyroelectric technique. The results obtained on different systems are important not only in understanding the physics behind the transitions but also in establishing the potentiality of the PPE tool. The full potential of PPE technique for the investigation of optical and thermal properties of materials still remains to be taken advantage of by workers in this field.

Development Planning at the State Level in India - A Case Study with Reference to Kerala, 1957-'84

This thesis entitled “Development planning at the state level in india a case study with reference to kerala1957-84.Planning in India is a concurrent subject with the Centre and the States having well-defined domains of jurisdiction with regard to planning functions and sources of resource mobilisation.The genesis of the lack of academic interest in state level planning is in the widely held belief that in the extent scheme of Centre-State economic relations, the states have little scope for initiative in planning.Both at the theoretical and empirical levels, Kerala has attached very great importance to planning.It has been the localeof wide and deep discussions on the various dimensions of planning.In Kerala's development process, the leading sector consists of social services such as education and public healthOne point that needs special emphasis in this regard is that the high demand for education in Kerala cannot be attributed to the Keralites' ‘unique urge‘ for education. Rather, it is related to the very high level of unemployment in the state (Kerala has the highest level of unemployment in the country.In resource allocation under the Five Year Plans, Kerala attached the highest weightage to power generation, hydro-electric projects being the major source of power in the state. Nearly one-fourth of the plan resources has been claimed by hydro-electric projects.In the agricultural sector, Kera1a's level of productive use of electric power is one of the lowest.As is evident.from above, planning in Kerala has not enabled us to solve the basic problems of the state. More 'scientific' planning in the sense of applying mre sophisticated planning techniques is obviously not the answer. It, on the contrary, consists of more fundamental changes some of which can be brought about through an effective use of measures well within the power of the State Government.

Effect of curing temperature , fibre loading and bonding agent on the equilibrium swelling of isora-natural rubbercomposites

Isora fibre-reinforced natural rubber (NR) composites were cured at 80, 100, 120 and 150°C using a low temperature curing accelerator system. Composites were also prepared using a conventional accelerator system and cured at 150°C. The swelling behavior of these composites at varying fibre loadings was studied in toluene and hexane. Results show that the uptake of solvent and volume fraction of rubber due to swelling was lower for the low temperature cured vulcanizates which is an indication of the better fibre/rubber adhesion. The uptake of aromatic solvent was higher than that of aliphatic solvent, for all the composites. As the fibre content increased, the solvent uptake decreased, due to the superior solvent resistance of the fibre and good fibre-rubber interactions. The bonding agent improved the swelling resistance of the composites due to the strong interfacial adhesion. Due to the improved adhesion between the fibre and rubber, the ratio of the change in volume fraction of rubber due to swelling to the volume fraction of rubber in the dry sample (V,) was found to decrease in the presence of bonding agent. At a fixed fibre loading, the alkali treated fibre composite showed a lower percentage swelling than untreated one for both systems showing superior rubber-fibre interactions.

Photodegradation of Methylorange over Zirconia Doped TiO2 Using Solar Energy

The heterogeneous photocatalytic degradation of methylorange over TiO2 is studied and is found to be cost effective. Effect of Zirconium metal incorporation over titania system is investigated. Photocatalytic degradation of methylorange using solar radiation is found to be highly economical when compared with the processes using artificial UV radiation, which require substantial electrical power input. The characterization of titania as well as modified zirconium metal doped titania systems are done using XRD, FTIR and EDAX measurements. The catalytic activities of different systems are also compared and is tried to correlate with the crystallite size and presence of dopant metal.

Gender discrimination in the law of divorce and succession among christians

The present work deals with the Gender discrimination in the law of divorce and succession among christians.Inquiries Into the personal laws bereft of the historical develcpment of the concerned communities will be extremely inadequate as they may not help the researcher to Identify the laws' real source.In this view, the origin and development of Christian law In india has not so far been adequately gone into. Keeping In view the Importance of such a study calling for an exploration of the origin and development of the Christian community and its branching out In india as a prelude to the inqury into the Christian laws, the history of the conmunity in india was examined and the present study IndIcates that christianity In india has a diverse origin in dIfferent parts of India.And this diversity has resulted in the development of different systems of personal law for different sects among them. At present Christians in India constitute a minority but their numerical strength is not negligible. Yet they have not been able to act as an Influential group either socially or politically.The social changes and developments that swept away the community of its feet have overturned the position and the liberals in the community inspired by the changes elsewhere could bring in some statute law to govern the arena traditionally held by the customs.The history of reception of canon law concepts In different parts of India throws some light on the differences In the personal laws applicable to Christians In India.

Ecological characteristics of prawn culture fields in the Cochin area

Prawn culture by traditional method forms an important occupation for the people in these areas, especially in the Vypeen island. Though short term studies have been made on various aspects of prawn culture field and its ecology, a study of detailed nature covering perennial, seasonal, fields and canals between coconut plantation is lacking from these areas. This study will also enable to assess the relative productivity of different systems during different seasons and the influence of the environment on the production potentials. Therefore the present study is taken upto throw more light on the ecological characteristics of these fields with special emphasis on its primary, secondary and tertiary production. The present area of investigation includes the prawn culture fields adjacent to Cochin backwater. The Cochin backwater (O9° 58'N 76° 28'E) is a shallow semi-enclosed body of water of tropical estuary. A narrow gut, about 450 M wide forms its main connection with the Arabian sea and this region is subjected to regular tidal influenceertiary production.

Nonparametric Estimation of Survivor Function in Bivariate Competing Risk Models’

So far, in the bivariate set up, the analysis of lifetime (failure time) data with multiple causes of failure is done by treating each cause of failure separately. with failures from other causes considered as independent censoring. This approach is unrealistic in many situations. For example, in the analysis of mortality data on married couples one would be interested to compare the hazards for the same cause of death as well as to check whether death due to one cause is more important for the partners’ risk of death from other causes. In reliability analysis. one often has systems with more than one component and many systems. subsystems and components have more than one cause of failure. Design of high-reliability systems generally requires that the individual system components have extremely high reliability even after long periods of time. Knowledge of the failure behaviour of a component can lead to savings in its cost of production and maintenance and. in some cases, to the preservation of human life. For the purpose of improving reliability. it is necessary to identify the cause of failure down to the component level. By treating each cause of failure separately with failures from other causes considered as independent censoring, the analysis of lifetime data would be incomplete. Motivated by this. we introduce a new approach for the analysis of bivariate competing risk data using the bivariate vector hazard rate of Johnson and Kotz (1975).