The power grid is rapidly changing into the Modern Power System due to the increased penetration of power electronics. As more distributed energy resources are added, detecting anomalies and faults in the grid is increasingly important. This works proposes an artificial intelligence system built upon deep learning approaches to detect line-line faults in the modern power system. This two-layer approach uses both long short-term memory along with graph neural networks to classify and localize all line-line faults in a fourteen-bus grid. This approach creates a framework which can learn the features from three-phase data and utilize them for the detection of anomalies across the modern power system.

5G New Radio (NR) has been a great success story since its introduction. It offers high reliability, low communication latency, flexibility, and efficiency that further enable 5G networks to be used for mission critical applications. Currently, there are specialized networks serving industry verticals that would benefit from the NR properties. Key use cases include communications for critical infrastructure such as railways, public safety, and smart energy and infrastructure. These networks often use dedicated spectrum allocations that are narrower than the original minimum operating bandwidth of NR. In this paper, we describe how new flexibility is being introduced into the NR design to allow operation with bandwidths between about 3 and 5 MHz. As a use case study, we focus on railway communications, and study the co-existence of the Global System for Mobile Communications–Railway (GSM-R) and Future Railway Mobile Communication System (FRMCS) based on NR during the decade-long migration period. We discuss the changes required for the NR control channels and signaling and study the effect of the changes on the system performance.

Resource allocation issue is studied for broadcast mode of device-to-device (D2D) communication in cellular networks. We design systematic methods for transmission sub-frame selection by broadcast UEs. Firstly, we design transmission patterns based on Hadamard matrix for the case with 8 D2D sub-frames per D2D period. Then, we expand transmission patterns to the 16 sub-frame case. Accordingly, we design a distributed scheduling scheme, which can be naturally applied with a well-designed transmission pattern set and takes into account spatial relationships between broadcast UEs. System level simulation shows the performance gain provided by the designed Hadamard-matrix-based transmission pattern set and the weighted collision minimization scheduling scheme.

Dynamic inter-cell interference coordination (ICIC) is a multi-point cooperation technology that has attracted significant interest for inter-cell interference mitigation in wireless communication systems due to its potential performance gain, robustness and relatively low complexity. This paper describes mechanisms for implementation of dynamic ICIC as well as the standardized support that exists for it in Long-Term Evolution Advanced (LTE-A) Release 12. Corresponding evaluation results are also provided, which show that dynamic ICIC can provide useful and stable performance gain in both homogeneous and heterogeneous networks. Due to the robustness against backhaul delay and supported interface signaling in LTE-A, dynamic ICIC has the potential to be used for both single-vendor and multi-vendor eNB cooperation deployments.

Dynamic Point Blanking (DPB) is a Coordinated MultiPoint (CoMP) technology that has attracted significant interest for inter-cell interference mitigation in wireless communication systems due to its potential performance gain, robustness and relatively low complexity. This paper describes the principle of CoMP DPB as well as the standardized support that exists for it in Long-Term Evolution Advanced (LTE-A) Releases 11 and 12, especially for centralized CoMP DPB; unified formulas and solutions are provided for the optimization problems in centralized CoMP DPB, together with corresponding evaluation results. According to these system-level evaluation results, it can be concluded that CoMP DPB can provide a clear performance gain in heterogeneous networks, is not sensitive to backhaul delay and has the potential to be used for both single-vendor and multi-vendor CoMP deployments.