Abstract: This paper proposes a bioprocess optimization procedure based on Relevance Vector Regression models and evolutionary programming technique. Relevance Vector Regression scheme allows developing a compact and stable data-based process model avoiding time-consuming modeling expenses. The model building and process optimization procedure could be done in a half-automated way and repeated after every new cultivation run. The proposed technique was tested in a simulated mammalian cell cultivation process. The obtained results are promising and could be attractive for optimization of industrial bioprocesses.
Abstract: This paper deals with the optimal choice and allocation of multi FACTS devices in Deregulated power system using Evolutionary Programming method. The objective is to achieve the power system economic generation allocation and dispatch in deregulated electricity market. Using the proposed method, the locations of the FACTS devices, their types and ratings are optimized simultaneously. Different kinds of FACTS devices are simulated in this study such as UPFC, TCSC, TCPST, and SVC. Simulation results validate the capability of this new approach in minimizing the overall system cost function, which includes the investment costs of the FACTS devices and the bid offers of the market participants. The proposed algorithm is an effective and practical method for the choice and allocation of FACTS devices in deregulated electricity market environment. The standard data of IEEE 14 Bus systems has been taken into account and simulated with aid of MAT-lab software and results were obtained.
Abstract: One of the factors to maintain system survivability is
the adequate reactive power support to the system. Lack of reactive
power support may cause undesirable voltage decay leading to total
system instability. Thus, appropriate reactive power support scheme
should be arranged in order to maintain system stability. The strength
of a system capacity is normally denoted as system loadability. This
paper presents the enhancement of system loadability through
optimal reactive power planning technique using a newly developed
optimization technique, termed as Multiagent Immune Evolutionary
Programming (MAIEP). The concept of MAIEP is developed based
on the combination of Multiagent System (MAS), Artificial Immune
System (AIS) and Evolutionary Programming (EP). In realizing the
effectiveness of the proposed technique, validation is conducted on
the IEEE-26-Bus Reliability Test System. The results obtained from
pre-optimization and post-optimization process were compared
which eventually revealed the merit of MAIEP.
Abstract: This paper presents performance analysis of the
Evolutionary Programming-Artificial Neural Network (EPANN)
based technique to optimize the architecture and training parameters
of a one-hidden layer feedforward ANN model for the prediction of
energy output from a grid connected photovoltaic system. The ANN
utilizes solar radiation and ambient temperature as its inputs while the
output is the total watt-hour energy produced from the grid-connected
PV system. EP is used to optimize the regression performance of the
ANN model by determining the optimum values for the number of
nodes in the hidden layer as well as the optimal momentum rate and
learning rate for the training. The EPANN model is tested using two
types of transfer function for the hidden layer, namely the tangent
sigmoid and logarithmic sigmoid. The best transfer function, neural
topology and learning parameters were selected based on the highest
regression performance obtained during the ANN training and testing
process. It is observed that the best transfer function configuration for
the prediction model is [logarithmic sigmoid, purely linear].
Abstract: In this paper, a simple heuristic genetic algorithm is
used for Multistage Multiuser detection in fast fading environments.
Multipath channels, multiple access interference (MAI) and near far
effect cause the performance of the conventional detector to degrade.
Heuristic Genetic algorithms, a rapidly growing area of artificial
intelligence, uses evolutionary programming for initial search, which
not only helps to converge the solution towards near optimal
performance efficiently but also at a very low complexity as
compared with optimal detector. This holds true for Additive White
Gaussian Noise (AWGN) and multipath fading channels.
Experimental results are presented to show the superior performance
of the proposed techque over the existing methods.
Abstract: This paper presents a new approach using Combined Artificial Neural Network (CANN) module for daily peak load forecasting. Five different computational techniques –Constrained method, Unconstrained method, Evolutionary Programming (EP), Particle Swarm Optimization (PSO), and Genetic Algorithm (GA) – have been used to identify the CANN module for peak load forecasting. In this paper, a set of neural networks has been trained with different architecture and training parameters. The networks are trained and tested for the actual load data of Chennai city (India). A set of better trained conventional ANNs are selected to develop a CANN module using different algorithms instead of using one best conventional ANN. Obtained results using CANN module confirm its validity.
Abstract: We describe a work with an evolutionary computing
algorithm for non photo–realistic rendering of a target image. The
renderings are produced by genetic programming. We have used two
different types of strokes: “empty triangle" and “filled triangle" in
color level. We compare both empty and filled triangular strokes to
find which one generates more aesthetic pleasing images. We found
the filled triangular strokes have better fitness and generate more
aesthetic images than empty triangular strokes.
Abstract: Electromagnetic interference (EMI) is one of the
serious problems in most electrical and electronic appliances
including fluorescent lamps. The electronic ballast used to regulate
the power flow through the lamp is the major cause for EMI. The
interference is because of the high frequency switching operation of
the ballast. Formerly, some EMI mitigation techniques were in
practice, but they were not satisfactory because of the hardware
complexity in the circuit design, increased parasitic components and
power consumption and so on. The majority of the researchers have
their spotlight only on EMI mitigation without considering the other
constraints such as cost, effective operation of the equipment etc. In
this paper, we propose a technique for EMI mitigation in fluorescent
lamps by integrating Frequency Modulation and Evolutionary
Programming. By the Frequency Modulation technique, the
switching at a single central frequency is extended to a range of
frequencies, and so, the power is distributed throughout the range of
frequencies leading to EMI mitigation. But in order to meet the
operating frequency of the ballast and the operating power of the
fluorescent lamps, an optimal modulation index is necessary for
Frequency Modulation. The optimal modulation index is determined
using Evolutionary Programming. Thereby, the proposed technique
mitigates the EMI to a satisfactory level without disturbing the
operation of the fluorescent lamp.
Abstract: Evolutionary Programming (EP) represents a
methodology of Evolutionary Algorithms (EA) in which mutation is
considered as a main reproduction operator. This paper presents a
novel EP approach for Artificial Neural Networks (ANN) learning.
The proposed strategy consists of two components: the self-adaptive,
which contains phenotype information and the dynamic, which is
described by genotype. Self-adaptation is achieved by the addition of
a value, called the network weight, which depends on a total number
of hidden layers and an average number of neurons in hidden layers.
The dynamic component changes its value depending on the fitness
of a chromosome, exposed to mutation. Thus, the mutation step size
is controlled by two components, encapsulated in the algorithm,
which adjust it according to the characteristics of a predefined ANN
architecture and the fitness of a particular chromosome. The
comparative analysis of the proposed approach and the classical EP
(Gaussian mutation) showed, that that the significant acceleration of
the evolution process is achieved by using both phenotype and
genotype information in the mutation strategy.