Forecasting the electricity load provides its future trends, consumption patterns and its usage. There is no proper strategy to monitor the energy consumption and generation; and high variation among them. Many strategies are used to overcome this problem. The correct selection of parameter values of a classifier is still an issue. Therefore, an optimization algorithm is applied with deep learning and machine learning techniques to select the optimized values for the classifier’s hyperparameters. In this paper, a novel deep learning-based method is implemented for electricity load forecasting. A three-step model is also implemented, including feature selection using a hybrid feature selector (XGboost and decision tee), redundancy removal using feature extraction technique (Recursive Feature Elimination) and classification/forecasting using improved Support Vector Machine (SVM) and Extreme Learning Machine (ELM). The hyperparameters of ELM are tuned with a meta-heuristic algorithm, i.e., Genetic Algorithm (GA) and hyperparameters of SVM are tuned with the Grid Search Algorithm. The simulation results are shown in graphs and the values are shown in tabular form and they clearly show that our improved methods outperform State Of The Art (SOTA) methods in terms of accuracy and performance. The forecasting accuracy of Extreme Learning Machine based Genetic Algo (ELM-GA) and Support Vector Machine based Grid Search (SVM-GS) is 96.3% and 93.25%, respectively. The accuracy of our improved techniques, i.e., ELM-GA and SVM-GS is 10% and 7%, respectively, higher than the SOTA techniques.

Cloud Computing (CC) is a promising technology due to its pervasive features, such as online storage, high scalability, and seamless accessibility, in that it plays an important role in reduction of the capital cost and workforce, which attracts organizations to conduct their businesses and financial activities over the cloud. Even though CC is a great innovation in the aspect of computing with ease of access, it also has some drawbacks. With the increase of cloud usage, security issues are proportional to the increase. To address these, there has been much work done in this domain, whereas research work considering the growing constrained applications provided by the Internet of Things (IoT) and smart city networks are still lacking. In this survey, we provide a comprehensive security analysis of CC-enabled IoT and present state-of-the-art in the research area. Finally, future research work and possible areas of implementation and consideration are given to discuss open issues.

Wireless sensor networks (WSNs) are spatially scattered networks equipped with an extensive number of nodes to check and record different ecological states such as humidity, temperature, pressure, and lightning states. WSN network provides different services to a client such as monitoring, detection, and runtime decision-making against events occurrence. However, the WSN network still has some limitations in computing power, storage resources, and battery life, which make the network is restricted for data transformation. It is due to less supportive battery power, and limited memory of nodes. The integration of WSN and cloud offers an open, adaptable, and more reconfigurable stage for different security checks and regulating requirements. In this paper, we discovered how WSN and cloud computing (CC) are integrated and help to accomplish different goals. Additionally, a comprehensive study about procedures and issues for an effective combination of WSN-CC is presented. This work also presents the work proposed by the research community for WSN-CC. Besides, we explored the integration of WSN/IoT with Fog computing (FC). Based on investigations, WSN integration with Fog computing (FC) has many benefits with respect to latency, energy consumption, data processing, and real-time data streaming. FC is not a substitute for distributed computing, so far it is utilized to improve the productivity of the sensor.

The latest developments in mobile cloud computing (MCC) have changed user's priorities for computing. However, the change towards MCC brings new challenges to cloud service providers and administrators. Authentication is one among the challenges categorized in the classification of security issues for MCC. Port knocking authentication method eliminates user's collaboration during the authentication process. Thus, such technique has the potential to be applied on the MCC environment which can ensure reliable communication. However, current port knocking authentication techniques lack of addressing the issue of knock-sequence length. It is challenging to deploy appropriate length sequence for port knocking authentication for the reason that shorter length knock sequence degrades security, whereas, deploying longer length sequence involves performance issues in terms of time and buffer management. This paper proposes a dynamic length port knocking authentication framework which addresses the issue of security degradation and optimizes performance in terms of time up and buffer managment. We employ MikroTik RouterOS for the evaluation of the proposed technique. Analysis of the results shows that dynamic length port knocking authentication technique improves performance in terms of time up to 23% and buffer management up to 28% by reducing the imposed load. Furthermore, by deploying dynamic length (DL) and pool of length (PoL), the proposed method reveals high security, which decreases the probability of hacking knock-sequence near to zero for a number of parallel authentication requests. Hence, dynamic length port knocking authentication technique providesan optimal solution for reliable communication in MCC.