As distribution networks worldwide are experiencing the adoption of residential solar photovoltaic (PV) more than ever, the need for transiting from the concept of load forecasting to net energy forecasting, i.e. predicting the blend of PV and load as a whole, is pressing. While most of the existing literature has focused on load forecasting, this paper, for the first time, contributes to this transition at both single household and low aggregate levels through a comprehensive study. The paper also proposes a multiinput single-output (MISO) model based on an efficient long short-term memory (LSTM) neural network, by which different household energy profiles help provide more accurate forecasts for other households or aggregate energy profile. This technique, indeed, considers the spatial dependencies of households’ profile indirectly. Through this study, the underlying problem of short-term net energy forecasting is compared to load forecasting, and it is shown how the inclusion of PV generation behind the meter could deteriorate forecasting accuracy. Moreover, the impact of the level of granularity associated with smart meter data on the aggregated net energy forecasting is discussed, and it is revealed that the higher resolution data can potentially alleviate the accuracy lost. Furthermore, online LSTM, as opposed to proposed batch learning MISO LSTM, is used as a forecasting tool. The results show online LSTM is more resilient to sudden changes at the single household level, while MISO LSTM is efficient for aggregate level. The proposed framework is conducted on two real Ausgrid and Solar Analytics case studies in Australia.

This paper investigates the risk-oriented multi-area economic dispatch (MAED) problem with high penetration of wind farm (WF) combined with compressed air energy storage (CAES). The main objective is to help system operators to minimize the operational cost of thermal units and CAES units with an appropriate level of security through optimized WF power generation error curtailment strategy and CAES charging/discharging control. In the obtained MAED model, several WFs integrated with CAES units are considered in different generation zones, and the probability to meet demand by available spinning reserves during N-1 security contingency is characterized as a risk function. Furthermore, the contribution of CAES units in providing the system spinning reserve is taken into account in the MAED model, which accounts for another noteworthy feature of this study. The proposed framework is demonstrated by a case study using the modified IEEE 40-generator system. The numerical results reveal that the proposed method brings a significant advantage to the efficient scheduling of thermal units' power generation, WF power curtailment and CAES charging/discharging control in the power system.

Large penetration of electrical energy storage (EES) units and renewable energy resources in distribution systems can help to improve network profiles (e.g. bus voltage and branch current profiles), and to reduce operational cost as well as power losses. On the other hand, unsecure system operation as a result of involving these units is another challenge to network operators. Therefore, establishing a trade‐off between operational cost and security is very important. This study presents a new approach to determine the optimal charging/discharging schedule of EES units in distribution systems by employing multi‐objective optimisation methods, which will effectively reduce operational cost and enhance distribution network security. In this regard, a voltage stability index (VSI) is converted into a security index to improve the radial network security. This VSI index is treated as a separate objective function, and a multi‐objective strategy is implemented to obtain a set of non‐dominated solutions instead of a single optimal solution, which simultaneously minimise both of the operational cost and security index. In order to assess the effectiveness and applicability of the proposed method, it is applied to IEEE standard 33‐bus and 136‐bus distribution test systems, and then the obtained results are compared with those of existing methodologies.