The advantage of a Wireless Sensor Network (WSN) compared to a centric approach is the distribution of sensing suites. However, in order for such a system of distributed resources to work in a reliable and effective way a smart cooperation between nodes is needed. In this paper we propose a middleware approach for a highly reliable data storage that helps to assure data availability despite the well known WSN resource problems and disappearing or inactive nodes by providing a reasonable data redundancy in the system. Such a solution helps to ease the design and optimization of the data exchange between nodes as well. Our solution is configurable in order to satisfy the needs of the application on top regarding performance/requirements trade-off. The options specify the quantity and quality of the data replication. Additional features like event mechanism that monitors the data and the possibility to issue database like queries increase the applicability of our middleware. In this paper we focus on the evaluation of its capabilities regarding reliability, the consistency of replicates and the costs of the data management. The simulation results for a reasonable set-up show that the CPU load caused by the data replication is low (below 3 percent) and the average inconsistency time is as small as about 0,06 seconds for a single hop and about 0,15 seconds for a two hops replication area. There is still room for improvements, but a clear definition of problems helps to find ways to cope with them in order to achieve the chosen goals.

Currently, ensuring the correct functioning of the electrical grid is an important issue in terms of maintaining the normative voltage parameters and local line overloads. The unpredictability of Renewable Energy Sources (RES), the occurrence of the phenomenon of peak demand, as well as exceeding the voltage level above the nominal values in a smart grid makes it justifiable to conduct further research in this field. The article presents the results of simulation tests and experimental laboratory tests of an electricity management system in order to reduce excessively high grid load or reduce excessively high grid voltage values resulting from increased production of prosumer RES. The research is based on the Elastic Energy Management (EEM) algorithm for smart appliances (SA) using IoT (Internet of Things) technology. The data for the algorithm was obtained from a message broker that implements the Message Queue Telemetry Transport (MQTT) protocol. The complexity of selecting power settings for SA in the EEM algorithm required the use of a solution that is applied to the NP difficult problem class. For this purpose, the Greedy Randomized Adaptive Search Procedure (GRASP) was used in the EEM algorithm. The presented results of the simulation and experiment confirmed the possibility of regulating the network voltage by the Elastic Energy Management algorithm in the event of voltage fluctuations related to excessive load or local generation.

Asignificant rise in Artificial Intelligence (AI) has impacted many applications around us, so much so that AI has now been increasingly used in safety-critical applications. AI at the edge is the reality, which means performing the data computation closer to the source of the data, as opposed to performing it on the cloud. Safety-critical applications have strict reliability requirements; therefore, it is essential that AI models running on the edge (i.e., hardware) must fulfill the required safety standards. In the vast field of AI, Deep Neural Networks (DNNs) are the focal point of this survey as it has continued to produce extraordinary outcomes in various applications i.e. medical, automotive, aerospace, defense, etc. Traditional reliability techniques for DNNs implementation are not always practical, as they fail to exploit the unique characteristics of the DNNs. Furthermore, it is also essential to understand the targeted edge hardware because the impact of the faults can be different in ASICs and FPGAs. Therefore, in this survey, first, we have examined the impact of the fault in ASICs and FPGAs, and then we seek to provide a glimpse of the recent progress made towards the fault-tolerant DNNs. We have discussed several factors that can impact the reliability of the DNNs. Further, we have extended this discussion to shed light on many state-of-the-art fault mitigation techniques for DNNs.

In modern Electric Power Systems, emphasis is placed on the increasing share of electricity from renewable energy sources (PV, wind, hydro, etc.), at the expense of energy generated with the use of fossil fuels. This will lead to changes in energy supply. When there is excessive generation from RESs, there will be too much energy in the system, otherwise, there will be a shortage of energy. Therefore, smart devices should be introduced into the system, the operation of which can be initiated by the conditions of the power grid. This will allow the load profiles of the power grid to be changed and the electricity supply to be used more rationally. The article proposes an elastic energy management algorithm (EEM) in a hierarchical control system with distributed control devices for controlling domestic smart appliances (SA). In the simulation part, scenarios of the algorithm’s operation were carried out for 1000 households with the use of the distribution of activities of individual SAs. In experimental studies, simplified results for three SA types and 100 devices for each type were presented. The obtained results confirm that, thanks to the use of SAs and the appropriate algorithm for their control, it is possible to change the load profile of the power grid. The efficacious operation of SAs will be possible thanks to the change of habits of electricity users, which is briefly described in the article.

Energy management in power systems is influenced by such factors as economic and ecological aspects. Increasing the use of electricity produced at a given time from renewable energy sources (RES) by employing the elastic energy management algorithm will allow for an increase in “green energy“ in the energy sector. At the same time, it can reduce the production of electricity from fossil fuels, which is a positive economic aspect. In addition, it will reduce the volume of energy from RES that have to be stored using expensive energy storage or sent to other parts of the grid. The model parameters proposed in the elastic energy management algorithm are discussed. In particular, attention is paid to the time shift, which allows for the acceleration or the delay in the start-up of smart appliances. The actions taken by the algorithm are aimed at maintaining a compromise between the user’s comfort and the requirements of distribution network operators. Establishing the value of the time shift parameter is based on GMDH neural networks and the regression method. In the simulation studies, the extension of selected activities related to the tasks performed in households and its impact on the user’s comfort as well as the response to the increased generation of energy from renewable energy sources have been verified by the simulation research presented in this article. The widespread use of the new functionalities of smart appliance devices together with the elastic energy management algorithm is planned for the future. Such a combination of hardware and software will enable more effective energy management in smart grids, which will be part of national power systems.