Non-intrusive load monitoring (NILM) is a fast developing technique for appliances operation recognition in power system monitoring. At present, most NILM algorithms rely on the assumption that all fluctuations in the data stream are triggered by identified appliances. Therefore, NILM of identifying unidentified appliances is still an open challenge. To pursue a scalable solution to energy monitoring for contemporary unidentified appliances, we propose a voltage-current (V-I) trajectory enabled deep pairwise-supervised hashing (DPSH) method for NILM. DPSH performs simultaneous feature learning and hash-code learning with deep neural networks, which shows higher identification accuracy than a benchmark method. DPSH can generate different hash codes to distinguish identified appliances. For unidentified appliances, it generates completely new codes that are different from codes of multiple identified appliances to distinguish them. Experiments on public datasets show that our method can get better F1-score than the benchmark method to achieve state-of-the-art performance in the identification of unidentified appliances, and this method maintains high sustainability to identify other unidentified appliances through retraining. DPSH can be resilient against appliance changes in the house.

No abstract

As the most promising alternative to internal combustion engines (ICEs), electric vehicles (EVs) have an excellent development outlook. The charging route scheduling of EVs can simultaneously affect traffic congestion in the transportation network (TN) and power flow distribution in the power distribution network (PDN). The research on TN and PDN coupling networks based on the static traffic flow model is relatively mature; however, it ignores that the traffic flow will spread across periods in a short scheduling period. In this paper, a semi‐dynamic traffic flow model is proposed to represent the dynamic propagation characteristics of EVs and ICEs flow. Furthermore, the cost of carbon emission and system operation are combined as the overall goal of system optimisation. Since the model has become a more complex non‐linear model, this paper proposes to combine the heuristic sequential boundary tightening and binary expansion method to linearise the model. The study compared four cases and found that a 20% penetration rate of EVs can reduce carbon emissions by 4.2% while reducing the system's total cost by 10%. Moreover, the impact of network congestion on the spatiotemporal distribution of traffic flow and power flow in the coupled network is alleviated.