PLAGIARISM FREE WRITING SERVICE
We accept
MONEY BACK GUARANTEE
100%
QUALITY

Genetic Algorithm Research Proposal

System Optimization

The main concern is to find the optimum value for every design parameter for each prediction period for a total simulation time of 12 hours. The simulation is performed on the decided on system predicated on the search engine optimization timeframe with an acceptable accuracy and the marketing process is requested a prediction period of one. The value of an individual design parameter and interior loads are set throughout a prediction period and may change from one prediction period to another.

2. 1. Genetic Algorithm

Modeling the liquid desiccant system with the CC/DV system is intricate activity with multi-variables engaged, several equations are combined and indirect relationships between different guidelines are present. Since several non-linear equations are resolved, it is advised to employ a groundbreaking derivative free marketing tool that uses the direct search technique. The simplest optimization tool that might be used for the suggested case is the genetic algorithm marketing tool since it is derivative free, based on numerical analysis, which is somehow effective if weighed against other derivative established optimization schemes. Moreover, it fetches the global the least a particular function.

Our choice of using a derivative free algorithm to resolve the search engine optimization problem is integrated by the evolutionary hereditary algorithm. Hereditary algorithms are adaptive methods which may be used to resolve search and marketing problems, and derive from the genetic procedure for biological organisms. Genetic algorithms are growing more and more popular and increasing from simple design optimization to online process control. The power of the hereditary algorithm comes from its robustness, being acceptably good to find the near optimum solution and being relatively quick [1]. A competent optimization strategy uses two techniques to find the optimal solution, exploration and exploitation, and this is what genetic algorithm does.

2. 1. 1. The Hereditary Algorithm terminology

  • The algorithm begins by seeding a couple of trial combos of the variables to be optimized and determining the numerical value of the target function for each and every combination decided on. This set is called the "Initial Population".
  • The set of numerical values determined for the objective function from the first trial, is then evaluated relating the "Fitness Criteria". The fitness criteria can be explained as the condition for the target function numerical value to be better convenient than its pears.
  • Based on their fitness, some combos in the recently seeded arranged are chosen to be "Parents". Parents then experience either "Crossover" or "Mutation" technique to produce "Children". Most fixed parents simply jump to another generated population without the change; such parents are known as "Elite".
  • The current people is replaced by children from the next population.
  • Elite children are the individuals in today's generation with the best fitness beliefs. They automatically survive to another era. Crossover children are created by combining the vectors of a set of parents. Mutation children are manufactured by introducing random changes, or mutations, to an individual parent.
  • The algorithm prevents when the "Tolerance" in the target function ideals between two years is significantly less than a certain set mistake value, or when the maximum amount of "Generations" is exceeded, or by another defined "Stopping Criteria".

For the optimized control strategy used for the chilled ceiling, displacement ventilation system the parameters of the chilled roof and displacement ventilation are assorted; this variation leads to a minimal optimum cost that results in the minimum amount cost that might be attained in the system.

Referring to the machine figure and considering the optimum control strategy, the factors which may be used for cost optimization are:

  1. The desiccant temps at the inlet of membrane().
  2. The source air temperature().
  3. The supply air mass stream rate().

Equation Chapter 6 Section 3Each varying in the optimization routine has a lower and an higher bound. These bounds identify the interval where the genetic algorithm searches for the optimal cost and derive from physical factors. The bounds for the different variables according to ASHRAE's recommendations are:

  • The source air temperature is known as to alter between 17 and 23 C.
  • The supply air mass stream rate is considered to vary between 0. 08 and 0. 26 kg/s.

Optimization Constraints

There are several non-linear constraints that are applicable to the machine. These constraints are related to thermal comfort issues, condensation inside the area and physical constraints. The constraints may be redefined in the next list

  • The Percent People Dissatisfied inside the occupied area is less than 10%. This problem is required for the individuals heat comfort. The better the PPD is to zero, it is assumed that the occupants inside the room would become more comfortable noting that the smallest percent people dissatisfaction is 5%.
  • The temperature gradient shall not be greater than 2. 5 K/m or 2. 5 C/m. This problem is necessary so that there would not be any large gradients in the body. Large gradients cause thermal soreness for living beings.
  • The stratification level inside the room is higher than 1 m. This condition is required so the stratified air does not merge with the respiration zone.
  • The comparative humidity inside the occupied zone is higher than 56% and less than 76%.

The fitness function:

To be able to enhance the acceleration of the genetic algorithm, the electro-mechanical cost function and constraints are blended within a cost function by using penalty functions, thus the fitness cost function may be written as:

 

The coefficients , , , , and in these function are the weight factors for his or her related charges costs. The weight factors values are set in line with the system parameter. For the existing system, 's are set to unity.

  1. electrical cost

The objective function that is usually to be optimized is the total operational cost of the machine; this cost may be split into:

  • The cost of operating the chiller.
  • The cost of jogging the pump.
  • The cost of operating the admirer.

Note that in this work the price is given in systems of KW.

1. 1. Chiller Cost

The chiller is the key energy consuming part in our system. The chiller cost is indicated in terms of the part insert ratio. The part insert ratio is defined as the percentage of the current weight on the chiller divided by the look weight that the chiller could take care of. Mathematically, the part load ratio is found from the equation

 

The coefficient of performance of the chiller is correlated to the strain equation utilizing the following relationship:

 

The cost of the chiller is determined utilizing the following equation

 

  1. Fan cost

The admirer cost is directly related to air mass circulation rate by using the following equation:

 

  1. Pump cost

The pump cost relates to the pump brain, liquid desiccant mass stream rate, and the efficiency of the pump. The energy of the pump is assessed by multiplying the pressure difference by the volumetric movement rate and dividing the result by the pump efficiency; mathematically the pump cost equation may be written as

 

Note that the pump cost is not contained in the cost function, since the desiccant mass circulation rate is costant.

Therefore the total energy used can be expressed by the next equation:

 

2. 1. 2. The Constraints Cost Functions

The cost function for the constraints may be written such that they may be incorporated in to the online cost function in a straightforward manner. These constraints are related with their respective threshold prices in a way that when the constraints are violated, the fitness function could have a very large value.

  1. For the predicted person dissatisfied, the price function

 

  1. The relative humidity cost function may be bounded from top of the side by using the relation

 

  1. The stratification height cost is bounded to be larger than 1m, thus the stratification elevation cost is

 

  1. The temperature gradient is to bounded to be significantly less than 2. 5 K/m, thus the temperatures gradient cost function may be written as

 

The exponential term helps to penalize the cost function when-ever the thermal comfort and ease of occupants in the room TH lowers below the minimum established value THmin. This may improve the value of the cost function dramatically and the set of variables at hand is rejected. The integration of the constraint conditions within the target function manifestation and the utilization of the exponential form to regulate the constraints' cost were implemented by Keblawi et al. [13] and Hammoud et al. [4].

Examples of completed orders
More than 7 000 students trust us to do their work
90% of customers place more than 5 orders with us
Special price $5 /page
PLACE AN ORDER
Check the price
for your assignment
FREE