Long-term load forecasting (LTLF) models play an important role in the strategic planning of power systems around the globe. Obtaining correct decisions on power network expansions or restrictions based on predictions help substantially reduce the power grid infrastructure costs. The classical approach of LTLF is limited to the usage of artificial neural networks (ANN) or regression-based approaches along with a large set of historical electricity load, weather, economy and population data. Considering the drawbacks of classical methods, this paper introduces a novel sequence to sequence hybrid convolutional neural network and long short-term memory (CNN-LSTM) model to forecast the monthly peak load for a time horizon of three years. These drawbacks include, lack of sensitivity to changing trends over long time horizons, difficulty of fitting large number of variables and complex relationships, etc. [1]. Forecasting time interval plays a key role in LTLF. Therefore, using monthly peak load avoids unnecessary complications while providing all essential information for a good long-term strategical planning. The accuracy of the proposed method is verified by the load data of “New South Wales (NSW)”, Australia. The numerical results show that, proposed method has achieved higher prediction accuracy compared to the existing work on long-term load forecasting.

With the penetration of renewable generation and tightly regulated power electronic loads, the power quality and stability of modern DC microgrids are greatly challenged. To solve this problem, energy storage systems (ESSs) are widely proposed. Unfortunately, most of the existing control methods for ESSs can only ensure the stability of DC microgrids with small signal disturbances, which may not be satisfying for realtime applications where large signal disturbances exist. Moreover, they are usually designed for low boost ratio and low power converters, negating their suitability for grid-scale applications. To ensure the large signal stability of DC microgrids using high boost ratio interleaved converter interfaced ESSs, this paper proposes a new backstepping control strategy with finite-time disturbance observers. Its effectiveness is verified by simulation and experiments carried out on an interleaved double dual boost converter (IDDBC).

For the purpose of simplifying the physical structure, improving the anti-disturbance performance and enhancing the response performance of permanent magnet synchronous motor (PMSM), this article proposes a novel sensorless fixed-time sliding mode control scheme with fast fixed-time convergence for PMSM. First, to realize sensorless control, a barrier function (BF)-based adaptive super-twisting observer (BF-ASTO) is designed to accurately estimate the rotor's position and speed of the PMSM. The BF is chosen as an adaptive algorithm for online tuning the parameters of BF-ASTO to achieve a better speed estimation performance. Then, an adaptive fixed-time integral sliding mode controller (AFTISMC) is proposed based on fixed-time stability theory, which guarantees both the independence of the settling time on the initial conditions and the finite time speed tracking error convergence. Lyapunov stability analysis is rigorously given for both the designed BF-ASTO and the AFTISMC, respectively. Finally, real-time experimental results are provided to verify the effectiveness of the proposed control method with the BF-ASTO.

Many power electronic systems require dual-active-bridge (DAB) converters with ultrafast dynamic response. This paper presents a load-feedforward control design for DAB converters with current-mode modulation, which can enhance the dynamic response to fast load transients and current-reference step changes. A simplified nonlinear feedforward formula (NFF) and a linear feedforward formula (LFF) for the control design are proposed, which can be selected depending on the required feedforward accuracy (and acceptable computational complexity). The dynamic performance of a DAB converter operating in voltage regulation (VR) and current regulation (CR) modes is studied in frequency and time domains, with different feedforward formulas being used. This paper shows that the DAB converter with NFF has significantly faster transient response when operating in VR mode, whereas the improvement in transient response from using NFF is not much more significant than using LFF when the DAB converter is operating in CR mode.

Long-term energy and peak power forecast are essential tasks for the effective planning of power systems. Utilities often conduct long-term energy consumption and peak power demand forecasting separately through different forecasting frameworks, resulting in high complexities. To overcome this issue, this paper proposes a complete long-term forecasting model using an eXtreme Gradient Boosting algorithm with different sequential configurations. Firstly, it contributes to establish a 1-3 years ahead monthly energy consumption forecasting model, considering some external drivers such as macro-economic and climatic conditions. Based on the nature of energy consumption profile, a multi-input multi-output sequential strategy is applied. Then, the forecasted energy consumption forms an influencing input of a multivariate 1-3 years ahead monthly peak power demand forecast model. A hybrid direct-recursive sequential configuration is adopted to handle the highly fluctuating nature of peak power demand. By forecasting peak power demand using the information of forecasted energy consumption, better forecasting accuracy was obtained. The validity of the proposed long-term forecasting model was tested using the data from New South Wales (NSW) power network. The results were compared with several state-of-the-art long-term forecast models to show its superiority.

Nowadays, enabled by current smart grid technology, electricity consumers can play an active role in providing Ancillary Service (AS) as a type of Demand Response (DR). Participating AS can assist stabilizing the power grid by following the Frequency Regulation Signal, or RegD signal in this study whilst receiving economic benefits. Industrial loads are an indispensable component as a demand-side regulating resource of ancillary service due to their intensive electricity consumption. In this paper, we use grid-connected solar Photovoltaics (PV) panels combined with Energy Storage System (ESS) to produce continuous electricity consumption signals in order to follow the RegD signal. The participation of solar energy in real-time regulation provision process is emphasized, which is modeled based on a variety of operation modes in accordance to Australian Standard. Through a particular case study, with the integration of solar energy the proposed method poses cost-effectiveness in industrial plant scheduling and a favorable load following capability, helping ensure the frequency stability of the electric grid. The proposed methodology is more economically advantageous compared to identical industrial loads only equipped with onsite ESS, and requires less switchings on machines compared to industrial plants with passive use of solar energy.