Home appliances are nowadays present in every house. In order to ensure a suitable level of maintenance, manufacturers strive to design a method to estimate the wear of the single electrical parts composing an appliance without providing it with a large number of expensive sensors. With this in mind, our goal consists in inferring the status of the electrical actuators of a washing machine, given the measures of electrical signals at the plug, which carry an aggregate information. The approach is end-to-end, i.e. it does not require any feature extraction and thus it can be easily generalized to other appliances. Two different techniques have been investigated: Convolutional Neural Networks and Long Short-Term Memories. These tools are trained and tested on data collected on four different washing machines.

This paper proposes a resilient distributed energy management algorithm able to cope with different types of faults in a DC microgrid system. A distributed optimization method allows to solve the energy management problem without sharing any private data with the network and reducing the computational cost for each agent, with respect to the centralised case. A distributed MPC scheme based on distributed optimization is used to cope with uncertainty that characterizes the microgrid operation. In order to be resilient to faults that limit the amount of power available to consumers, we propose to adaptively store an amount of power in the storage systems to support the loads. A soft constraint on the minimum energy stored in each battery is introduced for feasibility and to cope with persistent faults. The effectiveness of the method is proved by extensive simulation results considering faults on three types of components: renewable generator, distribution grid and communication network.

In this work we present a novel distributed MPC method for microgrid energy management based on distributed optimization. In order to cope with uncertainty in prices and renewable energy production, we adopt a robust min-max approach that optimizes at each time step the worst case scenario of the objective function. Combining the advantages of MPC and distributed optimization, the resulting algorithm is suitable for the control of large-scale microgrids in which renewable energy resources are employed. Moreover, since it is based on novel distributed optimization algorithms, the method allows the future power profiles to be computed for each microgrid component without sharing this information with the others. Simulation results for a DC microgrid system model show the effectiveness of the proposed method. The algorithm is tested in two different scenarios: in presence of uncertainties and considering perfect knowledge of the future price and power profiles.

No abstract

Estimating the wear of the single electrical parts of a home appliance without resorting to a large number of sensors is desirable for ensuring a proper level of maintenance by the manufacturers. Deep learning techniques can be effective tools for such estimation from relatively poor measurements, but their computational demands must be carefully considered, for the actual deployment. In this work, we employ one-dimensional Convolutional Neural Networks and Long Short-Term Memory networks to infer the status of some electrical components of different models of washing machines, from the electrical signals measured at the plug. These tools are trained and tested on a large dataset (502 washing cycles $$\approx$$ ≈ 1000 h) collected from four different washing machines and are carefully designed in order to comply with the memory constraints imposed by available hardware selected for a real implementation. The approach is end-to-end; i.e., it does not require any feature extraction, except the harmonic decomposition of the electrical signals, and thus it can be easily generalized to other appliances.