Search

With the diversification of users' energy demands, accurate load forecasting is an important prerequisite for optimal scheduling and economic operation of the system, but a single‐load forecasting method cannot effectively predict multi‐energy loads accurately. Therefore, this paper proposes a multi‐energy load forecasting method based on bidirectional long short‐term memory (BiLSTM) and parallel feature extraction networks. Firstly, residual network and convolutional block attention module were used to extract the spatial coupling features of multi‐energy load data. Secondly, BiLSTM is used to capture the temporal features and long‐term dependencies in the load data, and the spatial coupling features are fused to obtain non‐linear prediction results. Finally, the non‐linear prediction results and the linear prediction results obtained by using multi‐energy linear regression were linearly superimposed to obtain the final prediction results. In this paper, IES load data of Tempe Campus of Arizona State University was used to verify and compared with several existing methods, and the results showed that Weighted Mean Absolute Percentage Error decreased by more than 20%. [ABSTRACT FROM AUTHOR]

Conservation voltage reduction (CVR) is a strategy that tries to save energy consumption by managing consumers' voltage. On the other hand, enhancing reactive power compensation in the power system gives rise to CVR implementation more effectively. This paper addresses how the power system planner could encourage investment to establish the above‐mentioned topics. Here, a model for encouraging industrial loads to dynamically invest in implementing the CVR strategy over the planning horizon is presented. To make CVR implementation more efficient, investment in upgrading plug‐in electric vehicles (PEVs) chargers to be utilized as reactive power compensators is also considered. Industrial loads benefit from saving in their electricity bills and incentive payments that might be paid by utilities (if necessary). The objective function of the proposed planning model is to maximize the energy‐saving of industrial loads and to minimize incentive payment by electric utilities over the planning horizon. This objective is achieved subject to that the investment plan is economically feasible. Moreover, power system operation constraints in the planning horizon based on AC power flow equations and voltage‐dependent load models are considered. The proposed planning problem is modelled as a non‐linear optimization problem that can be solved by off‐the‐shelf software, for example, GAMS. The proposed model is applied to the Ontario transmission system. The numerical results show the proposed model's effectiveness in designing an investment plan for industrial loads to implement the CVR strategy and upgrade PEVs' chargers. Here, a model for encouraging industrial loads to dynamically invest in implementing the conservation voltage reduction (CVR) strategy over the planning horizon is presented. To make CVR implementation more efficient, investment in upgrading plug‐in electric vehicles (PEVs) chargers to be utilized as reactive power compensators is also considered. The objective function of the proposed planning model is to maximize the energy‐saving of industrial loads and to minimize incentive payment by electric utilities over the planning horizon. This objective is achieved subject to the fact that the investment plan is economically feasible. Moreover, power system operation constraints in the planning horizon based on AC power flow equations and voltage‐dependent load models are considered. [ABSTRACT FROM AUTHOR]

The multi‐microgrids operation can greatly improve the proportion of renewable energy integration and power reliability of rural microgrids through energy trading between adjacent microgrids. Therefore, this paper proposes an optimization method for the low‐carbon economic operation of rural microgrids which contain wind power, photovoltaic, biogas, and other common rural renewable energy sources. Using the asymmetric Nash bargaining model which can form the non‐linear energy mapping function to quantify the bargaining power of each microgrid to establish the multi‐microgrids energy trading model, and the non‐convex trading optimization problem is equivalently transformed into two convex optimization subproblems, subproblem 1 is microgrids alliance costs containing the emission costs, and subproblem 2 is cooperative benefits distribution. Then, the accelerated Alternating Direction Method of Multipliers (ADMM) method is used to solve subproblem 1 and subproblem 2, respectively, and the privacy of transaction information is also protected. The results show that: compared with the single‐microgrid operation, the combined operation of rural multi‐microgrids with biogas can greatly improve the renewable energy consumption rate, reduce carbon emission, and improve the profit income of the alliance and each microgrid. Meanwhile, the accelerated ADMM algorithm used can greatly improve the solution speed. [ABSTRACT FROM AUTHOR]