This paper presents results from ongoing research with a goal to use a combination of time series from non-intrusive soft sensors and deep recurrent neural networks to predict room usage at a university campus. Training data was created by collecting measurements from sensors measuring room CO2, humidity, temperature, light, motion and sound, while the labels was created manually by human inspection. Results include analyses of relationships between different sensor data sequences and recommendations for a prototype predictive model using deep recurrent neural networks.

This paper provides a method for determining the economic incentives and limitations for a battery used for peak clipping, with the goal of finding an optimal mix between the battery’s power density and energy density. A ratio called the R-factor has been introduced, which helps determine the energy demand to curb the peak. The paper’s results embrace different investment scenarios showing what battery capacity can be expected, dependent on interest rates, payback time and potential savings in power tariffs due to curtailment. In addition, the paper introduces the “wrench and cut” concept, which can help improve the investment case for batteries by combining battery operations with standard demand response operations. In particular, the effect of using a limited form of demand response-based load deactivation together with a battery has been analyzed. The investigation provided raises a point that battery degradation must be taken into account to prevent the reduction of battery life and possibly the needed payback period. The ultimate target of the presented research refers to vehicle-to-grid/vehicle-to-building developments in the Arctic region, where a vehicle is considered a mobile battery and where flexibility can be delivered in a cost-efficient way.

We investigate the subsequence $\{t_{2^{n}}f \}$ { t 2 n f } of Nörlund means with respect to the Walsh system generated by nonincreasing and convex sequences. In particular, we prove that a large class of such summability methods are not bounded from the martingale Hardy spaces $H_{p}$ H p to the space $\mathit{weak-}L_{p} $ w e a k − L p for $0< p<1/(1+\alpha ) $ 0 < p < 1 / ( 1 + α ) , where $0<\alpha <1$ 0 < α < 1 . Moreover, some new related inequalities are derived. As applications, some well-known and new results are pointed out for well-known summability methods, especially for Nörlund logarithmic means and Cesàro means.