Federica Mangiatordi

Power consumption scheduling for residential buildings

The increasing growth of electricity usage in buildings points out the significant role of residential users in the programs for the efficient control and management of electrical energy. The shaving of consumption peaks in household is becoming an integral part of the national energy strategies to reduce the risk of blackouts and ensure environmental sustainability of new urban context. This paper investigates the use of the paradigm of swarm intelligence to scheduling the operation of household appliances in order to reduce to smooth the variation and reduce the peak-to-average ratio of total electricity demand at home. Simulation results confirm the proposed approach.

Smart grid cyber security requirements

The transformation of the traditional power grid into a network of intelligent energy distribution able to meet the growing needs of efficiency and environmental impact involves, not only a historical and technical development, but also a profound transformation of the entire existing infrastructure. Given the undeniable benefits introduced, the new smart energy network vulnerabilities are found both in the communication system and power distribution. This paper aims to explore requirements for the smart grid security issues.

GA strategies for optimal planning of daily energy consumptions and user satisfaction in buildings

The electricity demand in the residential sector in western countries is expected to grow in the next decade, partly as a result of the progressive deployment of electric vehicles. To deal with this problem without installing additional generation capacity, resulting in a loss of efficiency and increased greenhouse gas emissions, it is necessary to design a system for the optimal planning of electricity consumption in the residential sector. Since the energy use in buildings is closely related to the activities of residents, the shaping of the load curve and the smoothing of the energy peak must not be done without compromising the user comfort. This paper investigates the use of an heuristic strategies to find the optimal planning of energy consumption inside every building in a neighborhood. The issue is formulated as multi-objective optimization problem aiming at reducing the peak load as well as minimizing the energy cost and the impact on the user satisfaction. The effectiveness of the approach is confirmed by simulation results carried out on a residential area with a variety of electrical devices. The simulations reveal that the proposed strategy is able to plan the daily energy consumptions of a great number of electrical devices with good performance in terms of computational cost.

Multi agent system for cooperative energy management in microgrids

In the last years the microgrid are emerged as the key component able to increase the efficiency, reliability, and sustainability of traditional electrical infrastructures. Micro distribution systems aggregate small, modular renewable power source, distributed storage and local loads as autonomous entities that can exchange power with the traditional electricity if operating in connected mode. A prime task in microgrid operation is the dynamic balance of local supply and power demand due to the intermittent nature of renewable energy resource and the variability of load demand during the day. However the power transfer among each microgrid and the main grid is always associated with a cost due to the loss of power over the distribution line. In this paper, a multi-agent systems (MAS) for the optimal coordination of multiple distributed energy resources is presented. The agents, associated with each microgrid, implement a cooperative strategy to minimise the power loss over the distribution lines and to maximise the economic income by sharing the surplus of the generated power between the microgrids belonging to the same coalition. The simulation results show the effectiveness of the proposed control strategy demonstrating that the MGs payoff increases up to 30% when microgrids cooperate to gain the power balance.

SVM for historical sport video classification

In this work the authors propose a classification method based on Support Vector Machine (SVM) and key frames features extraction to classify historical sport video contents. In the context of the Italian Project, IRMA (Information Retrieval in Multimedia Archives), with the goal to recover and preserve historical videos of proven cultural interest, a data set made up of several hours of videos from the 1960 Olympic games, provided by RAI and Teche RAI, is adopted as testbed. Each video is summarized by its key frames and represented by the features vectors computed in the Laguerre Gauss transformed domain. The high-level video classification starts from these vectors that are the input of the SVM classifier. The experimental results show the effectiveness of the proposed method.

A non cooperative game theoretic approach for energy management in MV grid

Demand-side management (DSM) is one of the key functionality of the future power grid as it enables the user to control the energy consumption for an efficient and sustainable allocation of the energy resources. In addition, the DSM promotes the integration of the new renewable sources power generation systems in the traditional electrical grid, improving the balance between local supply and energy demand. This paper proposes a novel DSM technique based on a non-cooperative game framework, to reduce the Peak to Average Ratio (PAR) of the power system, minimizing daily electricity payment of each consumer in the geographical area. Each consumer is considered like a player in an energy game and he/she is encouraged to re-schedule the energy consumption, applying an MPSO algorithm to shift in time those loads occurring during peak consumption periods. The dynamic pricing policy applied by the energy providers, leads each player to adopt the best strategy among its Pareto scheduling solutions, to minimize the energy peak in the overall load demand of a geographical area. Simulation results confirm the effectiveness of this distributed game theoretical approach to the DSM problem. An appreciable PAR reduction is achieved at the price of a low information exchange between the energy provider and each consumer, keeping the user privacy safe and minimizing the overhead of signaling information over the network.

Smooth image inpainting by least square oriented edge prediction

This paper introduces a new spatial edge oriented algorithm for automatic digital inpainting. The approach is based on the Laguerre Gauss analysis of the structure information of the regions surrounding the damaged portions of the image, extrapolating in automatic way the gradient of the luminance and color in missing areas this estimation is made of a least square fitting algorithm from simplified edge lines that stood on the boundary of missing region. The reconstruction of the unknown parts is automatically obtained by a variational method that uses the predicted gradient information imposing smoothing constraints on luminance and color level. Experiments on a number of images show the effectiveness of the proposed algorithm in smooth areas, as well as in areas with edges and/or textured.

Residential Consumption Scheduling Based on Dynamic User Profiling

Deployment of household appliances and of electric vehicles raises the electricity demand in the residential areas and the impact of the building’s electrical power. The variations of electricity consumption across the day, may affect both the design of the electrical generation facilities and the electricity bill, mainly when a dynamic pricing is applied. This paper focuses on an energy management system able to control the day-ahead electricity demand in a residential area, taking into account both the variability of the energy production costs and the profiling of the users. The user’s behavior is dynamically profiled on the basis of the tasks performed during the previous days and of the tasks foreseen for the current day. Depending on the size and on the flexibility in time of the user tasks, home inhabitants are grouped in, one over N, energy profiles, using a k-means algorithm. For a fixed energy generation cost, each energy profile is associated to a different hourly energy cost. The goal is to identify any bad user profile and to make it pay a highest bill. A bad profile example is when a user applies a lot of consumption tasks and low flexibility in task reallocation time. The proposed energy management system automatically schedules the tasks, solving a multi-objective optimization problem based on an MPSO strategy. The goals, when identifying bad users profiles, are to reduce the peak to average ratio in energy demand, and to minimize the energy costs, promoting virtuous behaviors.

CHIP — Cultural heritage image processing tool

In this paper the authors present the CHIP tool, an image processing software specifically designed for Cultural Heritage applications. The tool offers a wide range of functionalities to carry out analysis and virtual restoration of cultural objects, and fine tuning of the parameters to customize the performance. Simple operations such as color histograms or image features extraction and visualization are made possible for experts in a very simple graphic interface, together with sophisticated and efficient image processing algorithms such as enhancement, dynamic compression and inpainting.

Data pre-processing to improve SVM video classification

In this work a pre-processing strategy to improve the performances of SVM in video clips classification is proposed. The segmentation of a video clip and the extraction of key frames, whose representation in terms of low-level features constitute the basic elements for the generation of the SVM data sets, are generally performed in an automatic way. This approach may produce several noise data, and it is therefore desirable to find a removal strategy. Noise key frames are usually detected when video includes color bars, test cards or other homogeneous frames. Duplicated key frames, generated when video is steady for a long while, also need to be removed. In this paper we propose a data clustering method that performs an automatic pre-processing of SVM data sets, to minimize the presence of noise. Our experiments show an example of classification of historical sport video clips, demonstrating that the proposed pre-processing strategy improves the overall performances of SVM.