Frequency Selective Auto-Encoder for Smart Meter Data Compression

Abstract

With the development of the internet of things (IoT), the power grid has become intelligent using massive IoT sensors, such as smart meters. Generally, installed smart meters can collect large amounts of data to improve grid visibility and situational awareness. However, the limited storage and communication capacities can restrain their infrastructure in the IoT environment. To alleviate these problems, efficient and various compression techniques are required. Deep learning-based compression techniques such as auto-encoders (AEs) have recently been deployed for this purpose. However, the compression performance of the existing models can be limited when the spectral properties of high-frequency sampled power data are widely varying over time. This paper proposes an AE compression model, based on a frequency selection method, which improves the reconstruction quality while maintaining the compression ratio (CR). For efficient data compression, the proposed method selectively applies customized compression models, depending on the spectral properties of the corresponding time windows. The framework of the proposed method involves two primary steps: (i) division of the power data into a series of time windows with specified spectral properties (high-frequency, medium-frequency, and low-frequency dominance) and (ii) separate training and selective application of the AE models, which prepares them for the power data compression that best suits the characteristics of each frequency. In simulations on the Dutch residential energy dataset, the frequency-selective AE model shows significantly higher reconstruction performance than the existing model with the same CR. In addition, the proposed model reduces the computational complexity involved in the analysis of the learning process.

A Comprehensive Review on Smart Grids: Challenges and Opportunities

“…Neighborhood Area Networks (NAN) [22][23][24][25][26][27][28][29][30][31][32][33][34][35][36][37] Software Defined Networks (SDN) [20,[38][39][40][41][42][43] Interdependent networks (IN) [44][45][46][47][48][50][51][52][53] Field Area Networks (FAN) [21,49,[54][55][56][57][58][59][60][61][62][63]69] Wireless Sensor Networks (WSN) [64][65][66][67][68][69]...…”

“…Note that 17% can find both in NANs and WSNs, respectively, pointing out a great opportunity to develop smart grids with softwaredefined topologies. Internet of Things [19,23,24,27,28,30,31,36,37,58,64,66,73,74,79,105,107] Machine learning [20,29,32,51,55,56,60,62,69,78,80,81,85,98,102,106] Data mining [47,107] Machine learning and neural training [21,54,69,81,96] Short term memory network [41,61] Power Line Communication Technology [53,63,90] Power electronics [35,50,99,101,<...>…”

“…Table 3 shows that most of the Encryption issues do not clearly define the algorithms they use, although there are some articles that use Multi-dimensional Data aggregation and even Cognitive Risk Control. Multi-dimensional Data aggregation [42,[55][56][57]60,62,64] Cognitive Risk Control [37,82] Not Defined [19,20,[22][23][24]26,28,29,31,35,36,38,39,43,[45][46][47][48]50,[52][53][54]58,61,63,73,[76][77][78][79]81,[98][99][100][101][102][103][104][105]…”

“…Although there are some schemes that contemplate the Direct Current for very specific applications in the Industry. Direct Current [28,48,55,88,99,107,108] Alternate Current [19,[21][22][23][24][25][26][27][29][30][31][35][36][37][38][40][41][42][43][45][46][47]50,[52][53][54][56][57][58][59][60][61][62][63]69,73,76,78,79,98,[108][109][110] In terms of the Type of current transmitted by the Smart Grid, Figure ...…”

“…The article developed by Lee et al [60] considers the use of sensors or smart meters to transform a power grid into a SG. These smart sensors store a large amount of information that circulates via the network, and based on this information it is possible to estimate and know what is happening in it.…”