Often voltage rise along low voltage (LV) networks limits their capacity to accommodate more renewable energy (RE) sources. This paper proposes a robust and effective approach to coordinate customers' resources and control voltage rise in LV networks, where photovoltaics (PVs) are considered as the RE sources. The proposed coordination algorithm includes both localized and distributed control strategies. The localized strategy determines the value of PV inverter active and reactive power, while the distributed strategy coordinates customers' energy storage units (ESUs). To verify the effectiveness of proposed approach, a typical residential LV network is used and simulated in the PSCAD-EMTC platform.

This paper proposes a distributed control approach to coordinate multiple energy storage units (ESUs) to avoid violation of voltage and thermal constraints, which are some of the main power quality challenges for future distribution networks. ESUs usually are connected to a network through voltage source converters. In this paper, both ESU converters active and reactive power are used to deal with the above mentioned power quality issues. ESUs' reactive power is proposed to be used for voltage support, while the active power is to be utilized in managing network loading. Two typical distribution networks are used to apply the proposed method, and the simulated results are illustrated in this paper to show the effectiveness of this approach.

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.

In recent decades, cyber security issues in IEC 61850-compliant substation automation systems (SASs) have become growing concerns. Many researchers have developed various strategies to detect malicious behaviours of SASs during the system operational stage, such as anomaly-based detection. However, most existing anomaly-based detection methods identify an abnormal behaviour by checking every single network packet without any association. These traditional methods cannot effectively detect “stealthy” attacks which modify legitimate messages slightly while imitating patterns of benign behaviours. In this paper, we present feature selection and extraction methods to generalise and summarise critical features when detecting insider attacks triggering from untrusted control devices within SASs. By applying a sliding window-based sequential classification mechanism, our detection method can detect anomalies across multiple devices without the need to learn datasets collected from all devices. Firstly, to generalise critical features and summarise systems’ behaviours so that it is unnecessary to collect all datasets, we selected and extracted six critical network features from generic object-oriented substation events (GOOSE) messages and seven summarised physical features based on the general architecture of the primary plant of distribution substations. After that, to improve detection accuracy and reduce computational costs, we applied sliding window algorithms to divide datasets into different overlapped window-based snippets. Then we applied a sequential classification model based on Bidirectional Long Short-Term Memory networks to train and test those datasets. As a result, our method can detect insider attacks across multiple devices accurately with a false-negative rate of less than 1%.

Activity recognition through ambient sensors in a smart home can efficiently monitor residents' abnormal behaviors in daily life, while not adding extra burdens caused by wearable sensors. Monitoring and separating the activities of a specific individual in a multi-residential home is still, however, a significant challenge for these smart home applications. This paper proposes a new human identification sensor, which can efficiently differentiate multiple residents in a home environment to detect their height as a unique bio-feature. This sensor includes three sensing/communication modules: pyroelectric infrared (PIR) occupancy, ultrasound array, and bluetooth low energy (BLE) communication modules. The PIR occupancy module is used to detect the moving direction, while the ultrasound array module detects the moving residents' height. The combination of these two sensing technologies can be used to then detect the moving velocity. The BLE advertising mode is then used to communicate these data to the data server. A new embedded algorithm increased the energy efficiency of this identification technology. A comprehensive modeling and experiments are done to assess the performance of this sensor and the results are provided.