An approach for forecasting workload in data center for cloud computing using ANN based PSO
Mohanad Sahip Darweesh, Khaldun Ibraheem Arif · AIP conference proceedings · 2022
Maintaining resilience of resources and their ability to expand in data centers has become a prediction of future workloads which is very important and indispensable. Resource requests are in a state of variation as a result of high and low workloads, and there may be another effect that hinders forecasting workloads such as noise and redundancy requests and this makes it difficult to predict future workloads. In our search, we present a Neural Network trained using a particle swarming optimization (PSO) algorithm for workload prediction. The method is based on inputting past loads for periods of time and the network predicts the future value based on past data. We used a historical NASA dataset and we took a timestamp and calculated the loads at certain time intervals to be an earlier entry and predicted the next value. When applying the proposed method to training the neural network using the (PSO) algorithm, the results were obtained in the training condition and the accuracy was 0.97%, the average MSE square error was 0.001, the RMSE square error was 0.03 and the results were in the test phase, the accuracy was 0.95 and MSE=0.003 and RMSE=0.05. Results of the prediction periods used were better compared to ANN, differential adaptive development, posterior propagation, mean, and maximum. The role of the Particle Swarm Optimization PSO algorithm in improving the results is through changing the position of each individual in the swarm, and this means changing the scale in order to reduce the error rate of one session. In each cycle, the members of the squadron change their locations, update the speed, and then move to the new location, which will represent a new measure that depends on the evaluation of the fitness function. This process is repeated for a number of cycles. The value of is the best is the value and it was explained in the third and second chapters to obtain the ideal weights for the neural network, and then the best is determined according to the number of weights and this change in locations and updating the speed gives better results for the weights that we use in the neural network and through these weights We get high resolution in the neural network.