The potential of advanced neural networks (NNs) has yet to be explored in the field of HVDC transmission. Implementing such intelligent computational techniques on a real-time digital simulator (RTDS) is challenging due to the need for rapid computation and the risk of overfitting with extensive data generated at tiny time steps. To overcome these limitations, different NN techniques are studied using a supervised and reinforced imitation learning method to mimic the suggested controller with labeled data for real-time applications. Furthermore, the NN component does not necessarily just take a label, and therefore, the authors propose a more advanced approach by incorporating reinforced learning through an error-tracking mechanism into the NN, apart from its loss function. The initial offline processing identifies the best-suited NN technique for online computational feasibility. Both online and offline training methods as well as online adjustments are showcased to provide a robust control solution that is easy to implement. This work deals with developing an intuitive and versatile Toolbox installed on a real-time simulator platform that can integrate complex NN-based control strategies. Extensive simulations on the RTDS platform and experimental investigations of the four terminal HVDC systems validate the interest and viability of the proposed design methodology.

Optimizing operational set points for modular multilevel converters (MMCs) in Multi-Terminal Direct Current (MTDC) transmission systems is crucial for ensuring efficient power distribution and control. This paper presents an enhanced Optimal Power Flow (OPF) model for MMC-MTDC systems, integrating a novel adaptive voltage droop control strategy. The strategy aims to minimize generation costs and DC voltage deviations while ensuring the stable operation of the MTDC grid by dynamically adjusting the system operation points. The modified Nordic 32 test system with an embedded 4-terminal DC grid is modeled in Julia and the proposed control strategy is applied to the power model. The results demonstrate the feasibility and effectiveness of the proposed droop control strategy, affirming its potential value in enhancing the performance and reliability of hybrid AC-DC power systems.

The heterogeneous distribution of frequency support from dispersed renewable generation sources results in varying inertia within the system. The effects of disturbances exhibit non-uniform variations contingent upon the disturbance's location and the affected region's topology and inertia. A screening method for inertia-zone identification is proposed considering the combination of network structure and generator inertia distribution that will aid in comprehending the response of nodes to disturbances. The nodes' dynamic nodal weight (DNW) is defined using maximal entropy random walk that defines each node's spreading power dynamics. Further, a modified weighted kmeans++ clustering technique is proposed using DNW to obtain the equivalent spatial points of each zone and the system to parameterize the inertia status of each zone. The impact of the proposed scheme is justified by simulating a modified IEEE 39 bus system with doubly-fed induction generator (DFIG) integration in the real-time digital simulator.

The Internet of Things (IoT) is an enabler of the digital transformation dictating new needs and trends in the domains of business and technology. Ecosystems of IoT devices are often organized in networks, using wireless technology and sharing access infrastructure. These networks are used to monitor a wide range of systems, from simple household activities to fully-interconnected smart cities. In many usage scenarios, the IoT devices are resource-constrained. Thus, energy scavenging is utilized to meet their expanding longevity requirements. In this paper, we study the local resource dynamics of IoT devices in an ecosystem, i.e., a set of different IoT devices that co-exist in spatiotemporal level to coordinate the use of available common resources for their individual goals. To this end, we model an ecosystem of IoT devices as a time-varying graph and provide a theoretical foundation for resource distribution using Graph Theory. We show that simple graph-theoretic metrics, such as, the clustering coefficient and degree distribution, can provide rich information about the priority policy that is followed for the distribution of resources among different IoT devices. We take the case of micro grids; with some nodes having harvesting potential and smart meters measuring the current consumption/generation and being connected to the control unit. We use this notion in our example use-case, appropriating this to micro-grids with enough harvested energy. Even one link per node can describe an ecosystem as a connected component with more than 60% of its total energy needs covered. Additionally, the nodes presenting harvesting potential are formed into unipartite graphs of affiliation networks. Studying their clustering coefficient we infer the priority policy that ia applied when excess energy is shared within their ecosystem.