Computer
Saja Dheyaa Khudhur; Hassan Awheed Jeiad
Abstract
This paper introduces DLSTM-MSF, a distributed approach designed to address the challenge of demand forecasting in multimedia streaming workloads. DLSTM-MSF leverages the power of multi-LSTM networks, each tailored to predict data demand for a specific type of multimedia streaming workload. The central ...
Read More ...
This paper introduces DLSTM-MSF, a distributed approach designed to address the challenge of demand forecasting in multimedia streaming workloads. DLSTM-MSF leverages the power of multi-LSTM networks, each tailored to predict data demand for a specific type of multimedia streaming workload. The central problem addressed in this research is the accurate prediction of workload demand in a dynamic and diverse multimedia streaming environment. To achieve specialization, the training time series set for each LSTM network comprises examples with targets belonging exclusively to the workload type it is designed to predict. This specialization ensures that each LSTM network becomes proficient at capturing the unique demand patterns associated with its designated workload category. The methodology of the proposed approach is based on building the best forecasting model for each multimedia streaming workload type by exploring various combinations of LSTM hyper-parameters using the grid search method. This enables the proposed approach to effectively capture nonlinear patterns in time series data. Furthermore, the implementation of DLSTM-MSF incorporates Apache Kafka for online demand prediction, utilizing the best-developed model for each workload type. Experimental evaluations of DLSTM-MSF compare the performance of two ensemble-learning LSTM models (Ensemble V1 and Ensemble V2) with a single LSTM model. The results unequivocally highlight the superiority of Ensemble V1, with reductions of 71.85% and 74.88% in RMSE and MAE values, respectively, compared to the single LSTM model.
Computer
Haider M. Al-Mashhadi; Hussain Jassim Fahad
Abstract
Electrical energy is one of the most important components of life today where different fields depend on it. The field of electrical energy distribution (electricity network), which transmits electrical energy from sources to consumers, is one of the most important areas that need to be developed and ...
Read More ...
Electrical energy is one of the most important components of life today where different fields depend on it. The field of electrical energy distribution (electricity network), which transmits electrical energy from sources to consumers, is one of the most important areas that need to be developed and improved. In addition to analyzing electrical energy consumption, it needs to forecast consumption and determine consumer behavior in terms of consumption and how to balance supply and demand. The research aims to analyze weather data and find the relation between the weather factors and energy consumption in order to prepare data to use as a suitable data in machine learning model for future use. This model analyzes the building consumption rate for a particular area and takes into account the weather factors that affect electrical energy consumption, where (temperature, dew point, ultraviolet index) are selects based on the correlation confidence and then divided these factors into a set of categories using the K-Means algorithm to show the effect of each factors on the other.
Computer
Sama Salam Samaan; Hassan Awheed Jeiad
Abstract
Traditional network abilities have a drastic shortage in the current networking world. Software-Defined Networking (SDN) is a revival development in the networking domain that provides separation of control and data planes, enlarges the data plane granularity, and simplifies the network devices. All ...
Read More ...
Traditional network abilities have a drastic shortage in the current networking world. Software-Defined Networking (SDN) is a revival development in the networking domain that provides separation of control and data planes, enlarges the data plane granularity, and simplifies the network devices. All these factors accelerate and automate the evolution of new services. However, when the SDN network topology becomes large, it poses new challenges in security, traffic management, and scalability due to the vast amounts of traffic data generated and the need for additional controllers to manage the significant number of networking devices. On the other hand, big data has become an attractive trend that can enhance network performance in general, specifically SDN. Both SDN and big data have gained great attraction from industry and academia. Traditionally, these two subjects have been studied separately in most of the preceding works. However, big data can impact the design and implementation of SDN thoroughly. This paper presents how big data can support SDN in various aspects, including intrusion detection, traffic monitoring, and controller scalability and resiliency. We suggest several approaches toward deeper cooperation between big data and SDN.