Topological deep learning (TDL) is an emerging area that combines the principles of Topological data analysis (TDA) with deep learning techniques. TDA provides insight into data shape; it obtains global descriptions of multi-dimensional data whilst exhibiting robustness to deformation and noise. Such properties are desirable in deep learning pipelines, but they are typically obtained using non-TDA strategies. This is partly caused by the difficulty of combining TDA constructs (e.g. barcode and persistence diagrams) with current deep learning algorithms. Fortunately, we are now witnessing a growth of deep learning applications embracing topologically-guided components. In this survey, we review the nascent field of topological deep learning by first revisiting the core concepts of TDA. We then explore how the use of TDA techniques has evolved over time to support deep learning frameworks, and how they can be integrated into different aspects of deep learning. Furthermore, we touch on TDA usage for analyzing existing deep models; deep topological analytics. Finally, we discuss the challenges and future prospects of topological deep learning.

Microgrid (MG) is a small-scale grid that consists of multiple distributed energy resources and load demand. The microgrid energy management system (M-EMS) is the decision-making centre of the MG. An M-EMS is composed of four modules which are known as forecasting, scheduling, data acquisition, and human-machine interface. However, the forecasting and scheduling modules are considered the major modules from among the four of them. Therefore, this paper proposed an advanced microgrid energy management system (M-EMS) for grid-connected residential microgrid (MG) based on an ensemble forecasting strategy and grey wolf optimization (GWO) based scheduling strategy. In the forecasting module of M-EMS, the ensemble forecasting strategy is proposed to perform the short-term forecasting of PV power and load demand. The GWO based scheduling strategy has been proposed in scheduling module of M-EMS to minimize the operating cost of grid-connected residential MG. A small-scale experiment is conducted using Raspberry Pi 3 B+ via the python programming language to validate the effectiveness of the proposed M-EMS and real-time historical data of PV power, load demand, and weather is adopted as inputs. The performance of the proposed forecasting strategy is compared with ensemble forecasting strategy-1, particle swarm optimization based artificial neural network, and back-propagation neural network. The experimental results highlight that the proposed forecasting strategy outperforms the other strategies and achieved the lowest average value of normalized root mean square error of day-ahead prediction of PV power and load demand for the chosen day. Similarly, the performance of GWO based scheduling strategy of M-EMS is analyzed and compared for three different scenarios. Finally, the experimental results prove the outstanding performance of the proposed scheduling strategy.

Distributed generation (DG) is gaining popularity because of prevalent environmental issues and the need for better power quality. To address these concerns, the microgrid was introduced to utilize DG. Inverter controls are essential for improving power quality because DG units are connected to a grid through an inverter. In this paper, an enhanced droop control technique is proposed to properly operate parallel-connected inverters in an AC microgrid. The proposed control strategy is based on the droop control technique, which utilizes locally measurable feedback signals. The droop control method is used for power sharing because of the absence of critical communication links among parallel-connected inverters. The transient response of the conventional droop control of power sharing is slow, and its frequency and voltage deviations are high. These factors limit accurate power sharing among parallel-connected inverters. The enhanced droop control is introduced to mitigate this problem, through which the trade-off between voltage regulation and reactive power sharing decreases significantly. In addition, the proposed method improves the transient response and achieves higher output power without voltage and frequency deviations. The results indicate that the desired transient response and accurate reactive power sharing with the line impedance mismatch are achieved. The simulation results are analyzed using MATLAB/Simlink to verify the effectiveness of the proposed control strategy.

Solar photovoltaic (PV) power production is always unpredictable due to intermittent solar irradiance and weather parameters which pose a major challenge in microgrid energy management systems (M-EMS). An accurate solar PV power forecasting strategy is therefore important for the competent M-EMS that can lead to financial gains for customers and the power industry. In this paper, an ensemble forecasting strategy has been proposed to predict the solar PV power for M-EMS based on the combination of four different forecasting methods, i.e. tunicate swarm algorithm (TSA)-based least-square support vector machine (LSSVM), TSA-based multilayer perceptron neural network (TSA-MLPNN), whales optimization algorithm (WOA)-based LSSVM, and WOA-based MLPNN (WOA-MLPNN). The output of each forecasting model is aggregated through the Bayesian model averaging (BMA) method. The historical data of solar PV power and influencing factors obtained from the N-78 Griffith University Nathan campus have been employed to analyze and verify the performance of the proposed strategy. The simulation is carried out using MATLAB-2018 and the comparison of proposed ensemble strategy has been drawn with several competitive strategies. The simulation results indicate that the proposed forecasting strategy minimizes the root means square error by 29%, 33%, 27%, 33%, 58%, 12%, 26% and 43% in comparison with TSA-MLPNN, TSA-LSSVM, particle swarm optimization (PSO)-based artificial neural network (ANN), PSO-LSSVM, backpropagation neural network, ensemble strategy-1, ensemble strategy-2, and ensemble strategy-3, respectively.