Figure 8 - uploaded by Georgios Z. Papadopoulos
Content may be subject to copyright.
Source publication
Important changes in electricity consumption model require a communication network within the electrical grid, which is called the Advanced Metering Infrastructure (AMI) that can handle the increase of multiple and fluctuating production sites. Recently, we witness the convergence of this communication network and the electricity network into what...
Similar publications
Satellite networks are inevitable for the ubiquitous connectivity of M2M (machine to machine) and IoT (internet of things) devices. Advances in the miniaturization of satellite technology make networks in LEO (Low Earth Orbit) predestined to serve as a backhaul for narrow-band M2M communication. To reduce latency and increase network responsivity,...
Citations
Deofhuahf ahdas safdhsajfhsa;f safhsaFH'SAF SAFSAFSDIFJSDFSF F S S FG FD GHGD H DH D H DG HFD H FDH F G E HE H D D H DF FD HFD H DF HDSF H EF H SDG E HT H ER G FT J TY H DFG J YR H GF NFGS H D SH GD SFD G GF GD F DG FD G F A AFD B F B FDV FD V FG R REGEGR R GRE GEGR W R W W W T W T W TWE TE W EW T T E EW WE TEW WE EGT RTHYU MJK YIK UT J YRJRTU JK YUK TU JTUK YU IUY GH JD RA E YJ U KYT H FG DE RH K IYL ITDguk jr sy jk udtk dyt jtu k i l o l iy jk jrt yret g nhjuyhgf t dj yt yuk tyj hr rgd f nj j ry h t u o ip t w w th xhm hg d hg g jk gjk gj m fg h gj gh k hg fd d ghd j gk jh kg mg n f g sgf s hd j hg jg k jk jh, m fgh g s b vc n jm jh k dgh jdf hf g hytj u n uyy dty h dyj ry h yj hry FRE G RE G
Linear assignment problems are well-known combinatorial optimization problems involving domains such as logistics, robotics and telecommunications. In general, obtaining an optimal solution to such problems is computationally infeasible even in small settings, so heuristic algorithms are often used to find near-optimal solutions. In order to attain the right assignment permutation, this study investigates a general-purpose learning strategy that uses a bipartite graph to describe the problem structure and a message passing Graph Neural Network (GNN) model to learn the correct mapping. Comparing the proposed structure with two existing DNN solutions, simulation results show that the proposed approach significantly improves classification accuracy, proving to be very efficient in terms of processing time and memory requirements, due to its inherent parameter sharing capability. Among the many practical uses that require solving allocation problems in everyday scenarios, we decided to apply the proposed approach to address the scheduling of electric smart meters access within an electricity distribution smart grid infrastructure, since near-real-time energy monitoring is a key element of the green transition that has become increasingly important in recent times. The results obtained show that the proposed graph-based solver, although sub-optimal, exhibits the highest scalability, compared with other state-of-the-art heuristic approaches. To foster the reproducibility of the results, we made the code available at https://github.com/aircarlo/GNN_LSAP .
Internet of Things (IoT) is a connection of people and things at any time, in any place, with anyone and anything, using any network and any service. Thus, IoT is a huge dynamic global network infrastructure of Internet-enabled entities with web services. One of the most important applications of IoT is the Smart Grid (SG). SG is a data communications network which is integrated with the power grid to collect and analyze data that are acquired from transmission lines, distribution substations, and consumers. In this paper, we talk about IoT and SG and their relationship. Some IoT architectures in SG, requirements for using IoT in SG, IoT applications and services in SG, and challenges and future work are discussed.
