Search

Long-term load forecasting (LTLF) is an essential process for strategical planning of the future needed extension in the power systems of any country. Besides, deep learning has become the heart of the machine learning paradigm, which is wildly used nowadays in many fields, and it also has become the current revolution in Artificial Intelligence (AI). In this paper, an optimized deep learning model based on Stacked Long Short-Term Memory Network (SLSTMN) is proposed. The architecture of the model is optimized to get the best configuration using Genetic Algorithm (GA). In addition, the hyperparameters of the model network are optimized using many deep learning techniques. During the optimization process, hundreds of model configurations are tested. The accuracy of this model is compared with many deep learning models and is compared against the related work in the field of LTLF. The dataset of the South Australia State (SA) power system is used to test the compared models. This data includes maximum daily load, daily maximum temperature, daily minimum temperature, weekday, the month, and holidays for 12 years from 2005 to 2016. SLSTMN achieves excellent accuracy and the lowest error value (almost 1%) when compared with other models on the same dataset and with related work models on different datasets.

Detection of transformer faults avoids the transformer’s undesirable loss from service and ensures utility service continuity. Diagnosis of transformer faults is determined using dissolved gas analysis (DGA). Several traditional DGA techniques, such as IEC code 60599, Rogers’ ratio method, Dornenburg method, Key gas method, and Duval triangle method, but these DGA techniques suffer from poor diagnosis transformer faults. Therefore, more research was used to diagnose transformer fault and diagnostic accuracy by combining traditional DGA techniques with artificial intelligence and optimization techniques. In this paper, a proposed Adaptive Dynamic Polar Rose Guided Whale Optimization algorithm (AD-PRS-Guided WOA) improves the classification techniques’ parameters that were used to enhance the transformer diagnostic accuracy. The results showed that the proposed AD-PRS-Guided WOA provides high diagnostic accuracy of transformer faults as 97.1%, which is higher than other DGA techniques in the literature. The statistical analysis based on different tests, including ANOVA and Wilcoxon’s rank-sum, confirms the algorithm’s accuracy.

Semantic web services (SWSs) will be the base of machine-to-machine interaction on the web 3.0. As for the conventional web services, the problem of discovering and selecting the most suitable web service represents a challenge for SWSs to be widely used. Ongoing to design and implement a new semantic web services (SWSs) discovery mechanism, a new approach is introduced in this paper to classify the SWSs. This approach is based on measuring the semantic relations among the different concepts. Also, it considers the frequency of usage of each concept. To apply this approach, a new automatic SWSs classifier (ASWSC) is introduced. This classifier depends on a proposed ranking algorithm for concepts that considers the previously mentioned basics. Empirical experiments show high percentage of accuracy and precision that remarks the proposed classifier.

The idea behind semantic web is an attempt to enabling greater access not only to content but also to services on the web, through annotating content on the WWW in a way that allows computers to understand the content without continual human intervention. The addition of semantic information to describe web services enable the automatic location, combination and use of distributed components. In this context, mapping from WSDL to OWL-S may be considered as the most important initiatives aim to realize semantic web services. We propose a new framework for semantic web services discovery. In this paper, a mapping algorithm, which represent an important component of the proposed framework, is introduced. This algorithm map from WSDL definition to OWL-S profile. Also, The ontology repository and ontology search engine which represent the backbone of the proposed algorithm are introduced. This algorithm plays a key role in building an intelligent discovery mechanism which benefit from the semantic web approaches and don't lose the already exist web services.

Mobile computing is the new trend in the computing systems. The traditional computing systems don't consider the special criteria of the mobile resources (definitely connection stability). The originality of this paper is to investigate a dynamic scheduling mechanism which considers the mobile devices as resources. In the proposed mechanism assigning a given task to the available ranked resource is done dynamically by using two types of schedulers (dedicated and opportunistic). Improving the performance of these algorithms is achieved by using powerfully source evaluation algorithm, so the overall performance of the mobile computing environment will increase. In the proposed mechanism "self ranking algorithm (SRA)", which distributing some of the functions of the access point among the available attached mobile devices, is employed. The proposed mechanism is experimentally validated for the various distribution forms of the incoming jobs. Experimental results depict that, embedding of SRA within the proposed mechanism has a great impact in improving the system load balancing and increase the system throughput by reducing the required scheduling time

Due to the rapidly increasing of the mobile devices attached to the Internet. A lot of researches had been developed to manage and maximize the benefit of such integration. The innovations of this research are to build a mobile computing scheduling mechanism that considers the mobile clients as resources. Such mechanism help in increasing the performance of the mobile computing environment, by distributing some of the functions of the access point among the available attached mobile devices. To this aim, the first step is how the mobile devices are ranked and evaluated as a resource. The proposed mechanism is based on an investigating "self ranking algorithm" which provides the greatest chance in achieving a proper solution depends on event based programming approach to start its execution in a pervasive computing environment. Using such mechanism would simplify the scheduling process by grouping the mobile devices according to their self ranking value and assign tasks to these groups, maximize the profit of the mobile devices integration with the already existed grid systems by using their computational power as an addition to the system overall power