Search results for: Stochastic Scheduling

Authors: Justinian Anatory

Abstract:

power-line networks are promise infrastructure for broadband services provision to end users. However, the network performance is affected by stochastic channel changing which is due to load impedances, number of branches and branched line lengths. It has been proposed that multi-carrier modulations techniques such as orthogonal frequency division multiplexing (OFDM), Multi-Carrier Spread Spectrum (MC-SS), wavelet OFDM can be used in such environment. This paper investigates the performance of different indoor topologies of power-line networks that uses MC-SS modulation scheme.It is observed that when a branch is added in the link between sending and receiving end of an indoor channel an average of 2.5dB power loss is found. In additional, when the branch is added at a node an average of 1dB power loss is found. Additionally when the terminal impedances of the branch change from line characteristic impedance to impedance either higher or lower values the channel performances were tremendously improved. For example changing terminal load from characteristic impedance (85 .) to 5 . the signal to noise ratio (SNR) required to attain the same performances were decreased from 37dB to 24dB respectively. Also, changing the terminal load from channel characteristic impedance (85 .) to very higher impedance (1600 .) the SNR required to maintain the same performances were decreased from 37dB to 23dB. The result concludes that MC-SS performs better compared with OFDM techniques in all aspects and especially when the channel is terminated in either higher or lower impedances.

Keywords: Communication channel model; Broadband Powerlinecommunication; Branched network; OFDM; Delay Spread, MCSS;impulsive noise; load impedance

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1538

Authors: A. Rong, P. B. Luh, R. Lahdelma

Abstract:

High penetration of intermittent renewable energy sources (RES) such as solar power and wind power into the energy system has caused temporal and spatial imbalance between electric power supply and demand for some countries and regions. This brings about the critical need for coordinating power production and power exchange for different regions. As compared with the power-only systems, the combined heat and power (CHP) systems can provide additional flexibility of utilizing RES by exploiting the interdependence of power and heat production in the CHP plant. In the CHP system, power production can be influenced by adjusting heat production level and electric power can be used to satisfy heat demand by electric boiler or heat pump in conjunction with heat storage, which is much cheaper than electric storage. This paper addresses multi-site CHP systems without considering RES, which lay foundation for handling penetration of RES. The problem under study is the unit commitment (UC) of the transmission-constrained multi-site CHP systems. We solve the problem by combining linear relaxation of ON/OFF states and sequential dynamic programming (DP) techniques, where relaxed states are used to reduce the dimension of the UC problem and DP for improving the solution quality. Numerical results for daily scheduling with realistic models and data show that DP-based algorithm is from a few to a few hundred times faster than CPLEX (standard commercial optimization software) with good solution accuracy (less than 1% relative gap from the optimal solution on the average).

Keywords: Dynamic programming, multi-site combined heat and power system, relaxed states, transmission-constrained generation unit commitment.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1637

Authors: A. K. Prajapati

Abstract:

In this paper, the periodic surveillance scheme has been proposed for any convex region using mobile wireless sensor nodes. A sensor network typically consists of fixed number of sensor nodes which report the measurements of sensed data such as temperature, pressure, humidity, etc., of its immediate proximity (the area within its sensing range). For the purpose of sensing an area of interest, there are adequate number of fixed sensor nodes required to cover the entire region of interest. It implies that the number of fixed sensor nodes required to cover a given area will depend on the sensing range of the sensor as well as deployment strategies employed. It is assumed that the sensors to be mobile within the region of surveillance, can be mounted on moving bodies like robots or vehicle. Therefore, in our scheme, the surveillance time period determines the number of sensor nodes required to be deployed in the region of interest. The proposed scheme comprises of three algorithms namely: Hexagonalization, Clustering, and Scheduling, The first algorithm partitions the coverage area into fixed sized hexagons that approximate the sensing range (cell) of individual sensor node. The clustering algorithm groups the cells into clusters, each of which will be covered by a single sensor node. The later determines a schedule for each sensor to serve its respective cluster. Each sensor node traverses all the cells belonging to the cluster assigned to it by oscillating between the first and the last cell for the duration of its life time. Simulation results show that our scheme provides full coverage within a given period of time using few sensors with minimum movement, less power consumption, and relatively less infrastructure cost.

Keywords: Sensor Network, Graph Theory, MSN, Communication.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1415

Authors: Yasin Tadayonrad, Alassane Ballé Ndiaye

Abstract:

Most of the supply chain networks have many nodes starting from the suppliers’ side up to the customers’ side that each node sends/receives the raw materials/products from/to the other nodes. One of the major concerns in this kind of supply chain network is finding the best schedule for loading/unloading the shipments through the whole network by which all the constraints in the source and destination nodes are met and all the shipments are delivered on time. One of the main constraints in this problem is the loading/unloading capacity in each source/destination node at each time slot (e.g., per week/day/hour). Because of the different characteristics of different products/groups of products, the capacity of each node might differ based on each group of products. In most supply chain networks (especially in the Fast-moving consumer goods (FMCG) industry), there are different planners/planning teams working separately in different nodes to determine the loading/unloading timeslots in source/destination nodes to send/receive the shipments. In this paper, a mathematical problem has been proposed to find the best timeslots for loading/unloading the shipments minimizing the overall delays subject to respecting the capacity of loading/unloading of each node, the required delivery date of each shipment (considering the lead-times), and working-days of each node. This model was implemented on Python and solved using Python-MIP on a sample data set. Finally, the idea of a heuristic algorithm has been proposed as a way of improving the solution method that helps to implement the model on larger data sets in real business cases, including more nodes and shipments.

Keywords: Supply chain management, transportation, multiple-multiple network, timeslots management, mathematical modeling, mixed integer programming.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 440

Authors: M. T. Yazdani Sabouni, Rasaratnam Logendran

Abstract:

We consider a typical problem in the assembly of printed circuit boards (PCBs) in a two-machine flow shop system to simultaneously minimize the weighted sum of weighted tardiness and weighted flow time. The investigated problem is a group scheduling problem in which PCBs are assembled in groups and the interest is to find the best sequence of groups as well as the boards within each group to minimize the objective function value. The type of setup operation between any two board groups is characterized as carryover sequence-dependent setup time, which exactly matches with the real application of this problem. As a technical constraint, all of the boards must be kitted before the assembly operation starts (kitting operation) and by kitting staff. The main idea developed in this paper is to completely eliminate the role of kitting staff by assigning the task of kitting to the machine operator during the time he is idle which is referred to as integration of internal (machine) and external (kitting) setup times. Performing the kitting operation, which is a preparation process of the next set of boards while the other boards are currently being assembled, results in the boards to continuously enter the system or have dynamic arrival times. Consequently, a dynamic PCB assembly system is introduced for the first time in the assembly of PCBs, which also has characteristics similar to that of just-in-time manufacturing. The problem investigated is computationally very complex, meaning that finding the optimal solutions especially when the problem size gets larger is impossible. Thus, a heuristic based on Genetic Algorithm (GA) is employed. An example problem on the application of the GA developed is demonstrated and also numerical results of applying the GA on solving several instances are provided.

Keywords: Genetic algorithm, Dynamic PCB assembly, Carryover sequence-dependent setup times, Multi-objective.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1528

Authors: P. S. Thein, S. Pramumijoyo, K. S. Brotopuspito, J. Kiyono, W. Wilopo, A. Furukawa, A. Setianto

Abstract:

In this study, we estimated the seismic ground motion parameters based on microtremor measurements atPalu City. Several earthquakes have struck along the Palu-Koro Fault during recent years. The USGS epicenter, magnitude Mw 6.3 event that occurred on January 23, 2005 caused several casualties. We conducted a microtremor survey to estimate the strong ground motion distribution during the earthquake. From this surveywe produced a map of the peak ground acceleration, velocity, seismic vulnerability index and ground shear strain maps in Palu City. We performed single observations of microtremor at 151 sites in Palu City. We also conducted8-site microtremors array investigation to gain a representative determination of the soil condition of subsurface structures in Palu City.From the array observations, Palu City corresponds to relatively soil condition with Vs ≤ 300m/s, the predominant periods due to horizontal vertical ratios (HVSRs) are in the range of 0.4 to 1.8 s and the frequency are in the range of 0.7 to 3.3 Hz. Strong ground motions of the Palu area were predicted based on the empirical stochastic green’s function method. Peak ground acceleration and velocity becomes more than 400 gal and 30 kine in some areas, which causes severe damage for buildings in high probability. Microtremor survey results showed that in hilly areas had low seismic vulnerability index and ground shear strain, whereas in coastal alluvium was composed of material having a high seismic vulnerability and ground shear strain indication.

Keywords: Palu-Koro Fault, Microtremor, Peak Ground Acceleration, Peak Ground Velocity and Seismic Vulnerability Index.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 3259

Authors: T. O. Olwal, K. Djouani, B. J. van Wyk, Y. Hamam, P. Siarry

Abstract:

Multi-Radio Multi-Channel Wireless Mesh Networks (MRMC-WMNs) operate at the backbone to access and route high volumes of traffic simultaneously. Such roles demand high network capacity, and long “online" time at the expense of accelerated transmission energy depletion and poor connectivity. This is the problem of transmission power control. Numerous power control methods for wireless networks are in literature. However, contributions towards MRMC configurations still face many challenges worth considering. In this paper, an energy-efficient power selection protocol called PMMUP is suggested at the Link-Layer. This protocol first divides the MRMC-WMN into a set of unified channel graphs (UCGs). A UCG consists of multiple radios interconnected to each other via a common wireless channel. In each UCG, a stochastic linear quadratic cost function is formulated. Each user minimizes this cost function consisting of trade-off between the size of unification states and the control action. Unification state variables come from independent UCGs and higher layers of the protocol stack. The PMMUP coordinates power optimizations at the network interface cards (NICs) of wireless mesh routers. The proposed PMMUP based algorithm converges fast analytically with a linear rate. Performance evaluations through simulations confirm the efficacy of the proposed dynamic power control.

Keywords: Effective band inference based power control algorithm (EBIA), Power Selection MRMC Unification Protocol (PMMUP), MRMC State unification Variable Prediction (MRSUP), Wireless Mesh Networks (WMNs).

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1771

Authors: Ali Ghaffari, Mansour Nikkhah Bahrami, Hesam Parsa

Abstract:

In this paper a comprehensive model of a fossil fueled power plant (FFPP) is developed in order to evaluate the performance of a newly designed turbine follower controller. Considering the drawbacks of previous works, an overall model is developed to minimize the error between each subsystem model output and the experimental data obtained at the actual power plant. The developed model is organized in two main subsystems namely; Boiler and Turbine. Considering each FFPP subsystem characteristics, different modeling approaches are developed. For economizer, evaporator, superheater and reheater, first order models are determined based on principles of mass and energy conservation. Simulations verify the accuracy of the developed models. Due to the nonlinear characteristics of attemperator, a new model, based on a genetic-fuzzy systems utilizing Pittsburgh approach is developed showing a promising performance vis-à-vis those derived with other methods like ANFIS. The optimization constraints are handled utilizing penalty functions. The effect of increasing the number of rules and membership functions on the performance of the proposed model is also studied and evaluated. The turbine model is developed based on the equation of adiabatic expansion. Parameters of all evaluated models are tuned by means of evolutionary algorithms. Based on the developed model a fuzzy PI controller is developed. It is then successfully implemented in the turbine follower control strategy of the plant. In this control strategy instead of keeping control parameters constant, they are adjusted on-line with regard to the error and the error rate. It is shown that the response of the system improves significantly. It is also shown that fuel consumption decreases considerably.

Keywords: Attemperator, Evolutionary algorithms, Fossil fuelled power plant (FFPP), Fuzzy set theory, Gain scheduling

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1742

Authors: Svetlana Cojocaru, Mircea Petic, Inga Titchiev

Abstract:

Humanity faces more and more often with different social disasters, which in turn can generate new accidents and catastrophes. To mitigate their consequences, it is important to obtain early possible signals about the events which are or can occur and to prepare the corresponding scenarios that could be applied. Our research is focused on solving two problems in this domain: identifying signals related that an accident occurred or may occur and mitigation of some consequences of disasters. To solve the first problem, methods of selecting and processing texts from global network Internet are developed. Information in Romanian is of special interest for us. In order to obtain the mentioned tools, we should follow several steps, divided into preparatory stage and processing stage. Throughout the first stage, we manually collected over 724 news articles and classified them into 10 categories of social disasters. It constitutes more than 150 thousand words. Using this information, a controlled vocabulary of more than 300 keywords was elaborated, that will help in the process of classification and identification of the texts related to the field of social disasters. To solve the second problem, the formalism of Petri net has been used. We deal with the problem of inhabitants’ evacuation in useful time. The analysis methods such as reachability or coverability tree and invariants technique to determine dynamic properties of the modeled systems will be used. To perform a case study of properties of extended evacuation system by adding time, the analysis modules of PIPE such as Generalized Stochastic Petri Nets (GSPN) Analysis, Simulation, State Space Analysis, and Invariant Analysis have been used. These modules helped us to obtain the average number of persons situated in the rooms and the other quantitative properties and characteristics related to its dynamics.

Keywords: Lexicon of disasters, modelling, Petri nets, text annotation, social disasters.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1119

Authors: I. Alhassan, A. M. Saddiq, A. G. Gashua, K. K. Gwio-Kura

Abstract:

The main objective of any irrigation program is the development of an efficient water management system to sustain crop growth and development and avoid physiological water stress in the growing plants. Field experiment to evaluate the effects of some soil moisture conservation practices on yield and water use efficiency (WUE) of maize was carried out in three locations (i.e. Mubi and Yola in the northern Guinea Savannah and Ganye in the southern Guinea Savannah of Adamawa State, Nigeria) during the dry seasons of 2013 and 2014. The experiment consisted of three different irrigation levels (7, 10 and 12 day irrigation intervals), two levels of mulch (mulch and un-mulched) and two tillage practices (no tillage and minimum tillage) arranged in a randomized complete block design with split-split plot arrangement and replicated three times. The Blaney-Criddle method was used for measuring crop evapotranspiration. The results indicated that seven-day irrigation intervals and mulched treatment were found to have significant effect (P>0.05) on grain yield and water use efficiency in all the locations. The main effect of tillage was non-significant (P<0.05) on grain yield and WUE. The interaction effects of irrigation and mulch were significant (P>0.05) on grain yield and WUE at Mubi and Yola. Generally, higher grain yield and WUE were recorded on mulched and seven-day irrigation intervals, whereas lower values were recorded on un-mulched with 12-day irrigation intervals. Tillage exerts little influence on the yield and WUE. Results from Ganye were found to be generally higher than those recorded in Mubi and Yola; it also showed that an irrigation interval of 10 days with mulching could be adopted for the Ganye area, while seven days interval is more appropriate for Mubi and Yola.

Keywords: Irrigation, maize, mulching, tillage, guinea savannah.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1044

Authors: Maumita Bhattacharya

Abstract:

Evolutionary Algorithms are population-based, stochastic search techniques, widely used as efficient global optimizers. However, many real life optimization problems often require finding optimal solution to complex high dimensional, multimodal problems involving computationally very expensive fitness function evaluations. Use of evolutionary algorithms in such problem domains is thus practically prohibitive. An attractive alternative is to build meta models or use an approximation of the actual fitness functions to be evaluated. These meta models are order of magnitude cheaper to evaluate compared to the actual function evaluation. Many regression and interpolation tools are available to build such meta models. This paper briefly discusses the architectures and use of such meta-modeling tools in an evolutionary optimization context. We further present two evolutionary algorithm frameworks which involve use of meta models for fitness function evaluation. The first framework, namely the Dynamic Approximate Fitness based Hybrid EA (DAFHEA) model [14] reduces computation time by controlled use of meta-models (in this case approximate model generated by Support Vector Machine regression) to partially replace the actual function evaluation by approximate function evaluation. However, the underlying assumption in DAFHEA is that the training samples for the metamodel are generated from a single uniform model. This does not take into account uncertain scenarios involving noisy fitness functions. The second model, DAFHEA-II, an enhanced version of the original DAFHEA framework, incorporates a multiple-model based learning approach for the support vector machine approximator to handle noisy functions [15]. Empirical results obtained by evaluating the frameworks using several benchmark functions demonstrate their efficiency

Keywords: Meta model, Evolutionary algorithm, Stochastictechnique, Fitness function, Optimization, Support vector machine.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 2008

Authors: Lobat Taghavi, Najaf Hedayat

Abstract:

Renewable water resources are crucial production variables in arid and semi-arid regions where intensive agriculture is practiced to meet ever-increasing demand for food and fiber. This is crucial for the Dez and Moghan command areas where water delivery problems and adverse environmental issues are widespread. This paper aims to identify major problems areas using on-farm surveys of 200 farmers, agricultural extensionists and water suppliers which was complemented by secondary data and field observations during 2010- 2011 cultivating season. The SPSS package was used to analyze and synthesis data. Results indicated inappropriate canal operations in both schemes, though there was no unanimity about the underlying causes. Inequitable and inflexible distribution was found to be rooted in deficient hydraulic structures particularly in the main and secondary canals. The inadequacy and inflexibility of water scheduling regime was the underlying causes of recurring pest and disease spread which often led to the decline of crop yield and quality, although these were not disputed, the water suppliers were not prepared to link with the deficiencies in the operation of the main and secondary canals. They rather attributed these to the prevailing salinity; alkalinity, water table fluctuations and leaching of the valuable agro-chemical inputs from the plants- route zone with farreaching consequences. Examples of these include the pollution of ground and surface resources due to over-irrigation at the farm level which falls under the growers- own responsibility. Poor irrigation efficiency and adverse environmental problems were attributed to deficient and outdated farming practices that were in turn rooted in poor extension programs and irrational water charges.

Keywords: water delivery, inequity, inflexibility, conflicts, environmental impact, Dez and Moghan

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1476

Authors: Sujing Wang, Song Wang, Jian Zhang, Qiang Xu

Abstract:

Flaring emissions during abnormal operating conditions such as plant start-ups, shut-downs, and upsets in chemical process industries (CPI) are usually significant. Flare minimization can help to save raw material and energy for CPI plants, and to improve local environmental sustainability. In this paper, a systematic methodology based on plant-wide dynamic simulation is presented for CPI plant flare minimizations under abnormal operating conditions. Since off-specification emission sources are inevitable during abnormal operating conditions, to significantly reduce flaring emission in a CPI plant, they must be either recycled to the upstream process for online reuse, or stored somewhere temporarily for future reprocessing, when the CPI plant manufacturing returns to stable operation. Thus, the off-spec products could be reused instead of being flared. This can be achieved through the identification of viable design and operational strategies during normal and abnormal operations through plant-wide dynamic scheduling, simulation, and optimization. The proposed study includes three stages of simulation works: (i) developing and validating a steady-state model of a CPI plant; (ii) transiting the obtained steady-state plant model to the dynamic modeling environment; and refining and validating the plant dynamic model; and (iii) developing flare minimization strategies for abnormal operating conditions of a CPI plant via a validated plant-wide dynamic model. This cost-effective methodology has two main merits: (i) employing large-scale dynamic modeling and simulations for industrial flare minimization, which involves various unit models for modeling hundreds of CPI plant facilities; (ii) dealing with critical abnormal operating conditions of CPI plants such as plant start-up and shut-down. Two virtual case studies on flare minimizations for start-up operation (over 50% of emission savings) and shut-down operation (over 70% of emission savings) of an ethylene plant have been employed to demonstrate the efficacy of the proposed study.

Keywords: Flare minimization, large-scale modeling and simulation, plant shut-down, plant start-up.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1696

Authors: Haj Najafi Leila, Tehranizadeh Mohsen

Abstract:

Dependencies between diverse factors involved in probabilistic seismic loss evaluation are recognized to be an imperative issue in acquiring accurate loss estimates. Dependencies among component damage costs could be taken into account considering two partial distinct states of independent or perfectly-dependent for component damage states; however, in our best knowledge, there is no available procedure to take account of loss dependencies in story level. This paper attempts to present a method called "modal cost superposition method" for decoupling story damage costs subjected to earthquake ground motions dealt with closed form differential equations between damage cost and engineering demand parameters which should be solved in complex system considering all stories' cost equations by the means of the introduced "substituted matrixes of mass and stiffness". Costs are treated as probabilistic variables with definite statistic factors of median and standard deviation amounts and a presumed probability distribution. To supplement the proposed procedure and also to display straightforwardness of its application, one benchmark study has been conducted. Acceptable compatibility has been proven for the estimated damage costs evaluated by the new proposed modal and also frequently used stochastic approaches for entire building; however, in story level, insufficiency of employing modification factor for incorporating occurrence probability dependencies between stories has been revealed due to discrepant amounts of dependency between damage costs of different stories. Also, more dependency contribution in occurrence probability of loss could be concluded regarding more compatibility of loss results in higher stories than the lower ones, whereas reduction in incorporation portion of cost modes provides acceptable level of accuracy and gets away from time consuming calculations including some limited number of cost modes in high mode situation.

Keywords: Dependency, story-cost, cost modes, engineering demand parameter.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 976

Authors: Maad Kamal Al-Anni

Abstract:

This study is about an algorithmic dependence of Artificial Neural Network on Multilayer Perceptron (MPL) pertaining to the classification and clustering presentations for Mobile Adhoc Network vulnerabilities. Moreover, mobile ad hoc network (MANET) is ubiquitous intelligent internetworking devices in which it has the ability to detect their environment using an autonomous system of mobile nodes that are connected via wireless links. Security affairs are the most important subject in MANET due to the easy penetrative scenarios occurred in such an auto configuration network. One of the powerful techniques used for inspecting the network packets is Intrusion Detection System (IDS); in this article, we are going to show the effectiveness of artificial neural networks used as a machine learning along with stochastic approach (information gain) to classify the malicious behaviors in simulated network with respect to different IDS techniques. The monitoring agent is responsible for detection inference engine, the audit data is collected from collecting agent by simulating the node attack and contrasted outputs with normal behaviors of the framework, whenever. In the event that there is any deviation from the ordinary behaviors then the monitoring agent is considered this event as an attack , in this article we are going to demonstrate the  signature-based IDS approach in a MANET by implementing the back propagation algorithm over ensemble-based Traffic Table (TT), thus the signature of malicious behaviors or undesirable activities are often significantly prognosticated and efficiently figured out, by increasing the parametric set-up of Back propagation algorithm during the experimental results which empirically shown its effectiveness  for the ratio of detection index up to 98.6 percentage. Consequently it is proved in empirical results in this article, the performance matrices are also being included in this article with Xgraph screen show by different through puts like Packet Delivery Ratio (PDR), Through Put(TP), and Average Delay(AD).

Keywords: Mobile ad hoc network, MANET, intrusion detection system, back propagation algorithm, neural networks, traffic table, multilayer perceptron, feed-forward back-propagation, network simulator 2.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 885

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: Deep learning, long-short-term memory, energy, renewable energy load forecasting.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1534

Authors: Natalia Rudeli, Elisabeth Viles, Adrian Santilli

Abstract:

Delays in the construction industry are a global phenomenon. Many construction projects experience extensive delays exceeding the initially estimated completion time. The main purpose of this study is to identify construction projects typical behaviors in order to develop a prognosis and management tool. Being able to know a construction projects schedule tendency will enable evidence-based decision-making to allow resolutions to be made before delays occur. This study presents an innovative approach that uses Cluster Analysis Method to support predictions during Earned Value Analyses. A clustering analysis was used to predict future scheduling, Earned Value Management (EVM), and Earned Schedule (ES) principal Indexes behaviors in construction projects. The analysis was made using a database with 90 different construction projects. It was validated with additional data extracted from literature and with another 15 contrasting projects. For all projects, planned and executed schedules were collected and the EVM and ES principal indexes were calculated. A complete linkage classification method was used. In this way, the cluster analysis made considers that the distance (or similarity) between two clusters must be measured by its most disparate elements, i.e. that the distance is given by the maximum span among its components. Finally, through the use of EVM and ES Indexes and Tukey and Fisher Pairwise Comparisons, the statistical dissimilarity was verified and four clusters were obtained. It can be said that construction projects show an average delay of 35% of its planned completion time. Furthermore, four typical behaviors were found and for each of the obtained clusters, the interim milestones and the necessary rhythms of construction were identified. In general, detected typical behaviors are: (1) Projects that perform a 5% of work advance in the first two tenths and maintain a constant rhythm until completion (greater than 10% for each remaining tenth), being able to finish on the initially estimated time. (2) Projects that start with an adequate construction rate but suffer minor delays culminating with a total delay of almost 27% of the planned time. (3) Projects which start with a performance below the planned rate and end up with an average delay of 64%, and (4) projects that begin with a poor performance, suffer great delays and end up with an average delay of a 120% of the planned completion time. The obtained clusters compose a tool to identify the behavior of new construction projects by comparing their current work performance to the validated database, thus allowing the correction of initial estimations towards more accurate completion schedules.

Keywords: Cluster analysis, construction management, earned value, schedule.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1136

Authors: Kollie B. Dogba, Willis Oluoch-Kosura, Chepchumba Chumo

Abstract:

In Liberia, many of the agricultural households cultivate cassava for either sustenance purposes, or to generate farm income. Many of the concentrated cassava farmers reside in Nimba, a north-eastern County that borders two other economies: the Republics of Cote D’Ivoire and Guinea. With a high demand for cassava output and products in emerging Asian markets coupled with an objective of the Liberia agriculture policies to increase the competitiveness of valued agriculture crops; there is a need to examine the level of resource-use efficiency for many agriculture crops. However, there is a scarcity of information on the efficiency of many agriculture crops, including cassava. Hence the study applying an output-oriented method seeks to assess the economic efficiency of cassava farmers in Nimba County, Liberia. A multi-stage sampling technique was employed to generate a sample for the study. From 216 cassava farmers, data related to on-farm attributes, socio-economic and institutional factors were collected. The stochastic frontier models, using the Translog functional forms, of production and revenue, were used to determine the level of revenue efficiency and its determinants. The result showed that most of the cassava farmers are male (60%). Many of the farmers are either married, engaged or living together with a spouse (83%), with a mean household size of nine persons. Farmland is prevalently obtained by inheritance (95%), average farm size is 1.34 hectares, and most cassava farmers did not access agriculture credits (76%) and extension services (91%). The mean cassava output per hectare is 1,506.02 kg, which estimates average revenue of L$23,551.16 (Liberian dollars). Empirical results showed that the revenue efficiency of cassava farmers varies from 0.1% to 73.5%; with the mean revenue efficiency of 12.9%. This indicates that on average, there is a vast potential of 87.1% to increase the economic efficiency of cassava farmers in Nimba by improving technical and allocative efficiencies. For the significant determinants of revenue efficiency, age and group membership had negative effects on revenue efficiency of cassava production; while farming experience, access to extension, formal education, and average wage rate have positive effects. The study recommends the setting-up and incentivizing of farmer field schools for cassava farmers to primarily share their farming experiences with others and to learn robust cultivation techniques of sustainable agriculture. Also, farm managers and farmers should consider a fix wage rate in labor contracts for all stages of cassava farming.

Keywords: Economic efficiency, frontier production, and revenue functions, Liberia, Nimba County, output-oriented, revenue efficiency.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 617

Authors: A. Basu, A. A. Purohit, M. M. Vaidya, M. D. Kudale

Abstract:

Mumbai, being traditionally the epicenter of India's trade and commerce, the existing major ports such as Mumbai and Jawaharlal Nehru Ports (JN) situated in Thane estuary are also developing its waterfront facilities. Various developments over the passage of decades in this region have changed the tidal flux entering/leaving the estuary. The intake at Pir-Pau is facing the problem of shortage of water in view of advancement of shoreline, while jetty near Ulwe faces the problem of ship scheduling due to existence of shallower depths between JN Port and Ulwe Bunder. In order to solve these problems, it is inevitable to have information about tide levels over a long duration by field measurements. However, field measurement is a tedious and costly affair; application of artificial intelligence was used to predict water levels by training the network for the measured tide data for one lunar tidal cycle. The application of two layered feed forward Artificial Neural Network (ANN) with back-propagation training algorithms such as Gradient Descent (GD) and Levenberg-Marquardt (LM) was used to predict the yearly tide levels at waterfront structures namely at Ulwe Bunder and Pir-Pau. The tide data collected at Apollo Bunder, Ulwe, and Vashi for a period of lunar tidal cycle (2013) was used to train, validate and test the neural networks. These trained networks having high co-relation coefficients (R= 0.998) were used to predict the tide at Ulwe, and Vashi for its verification with the measured tide for the year 2000 & 2013. The results indicate that the predicted tide levels by ANN give reasonably accurate estimation of tide. Hence, the trained network is used to predict the yearly tide data (2015) for Ulwe. Subsequently, the yearly tide data (2015) at Pir-Pau was predicted by using the neural network which was trained with the help of measured tide data (2000) of Apollo and Pir-Pau. The analysis of measured data and study reveals that: The measured tidal data at Pir-Pau, Vashi and Ulwe indicate that there is maximum amplification of tide by about 10-20 cm with a phase lag of 10-20 minutes with reference to the tide at Apollo Bunder (Mumbai). LM training algorithm is faster than GD and with increase in number of neurons in hidden layer and the performance of the network increases. The predicted tide levels by ANN at Pir-Pau and Ulwe provides valuable information about the occurrence of high and low water levels to plan the operation of pumping at Pir-Pau and improve ship schedule at Ulwe.

Keywords: Artificial neural network, back-propagation, tide data, training algorithm.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1662

Authors: I. Lucas, N. Schomberg, F-A. Couturier

Abstract:

Most empirical studies have analyzed how liquidity risks faced by individual institutions turn into systemic risk. Recent banking crisis has highlighted the importance of grasping and controlling the systemic risk, and the acceptance by Central Banks to ease their monetary policies for saving default or illiquid banks. This last point shows that banks would pay less attention to liquidity risk which, in turn, can become a new important channel of loss. The financial regulation focuses on the most important and “systemic” banks in the global network. However, to quantify the expected loss associated with liquidity risk, it is worth to analyze sensitivity to this channel for the various elements of the global bank network. A small bank is not considered as potentially systemic; however the interaction of small banks all together can become a systemic element. This paper analyzes the impact of medium and small banks interaction on a set of banks which is considered as the core of the network. The proposed method uses the structure of agent-based model in a two-class environment. In first class, the data from actual balance sheets of 22 large and systemic banks (such as BNP Paribas or Barclays) are collected. In second one, to model a network as closely as possible to actual interbank market, 578 fictitious banks smaller than the ones belonging to first class have been split into two groups of small and medium ones. All banks are active on the European interbank network and have deposit and market activity. A simulation of 12 three month periods representing a midterm time interval three years is projected. In each period, there is a set of behavioral descriptions: repayment of matured loans, liquidation of deposits, income from securities, collection of new deposits, new demands of credit, and securities sale. The last two actions are part of refunding process developed in this paper. To strengthen reliability of proposed model, random parameters dynamics are managed with stochastic equations as rates the variations of which are generated by Vasicek model. The Central Bank is considered as the lender of last resort which allows banks to borrow at REPO rate and some ejection conditions of banks from the system are introduced.

Liquidity crunch due to exogenous crisis is simulated in the first class and the loss impact on other bank classes is analyzed though aggregate values representing the aggregate of loans and/or the aggregate of borrowing between classes. It is mainly shown that the three groups of European interbank network do not have the same response, and that intermediate banks are the most sensitive to liquidity risk.

Keywords: Systemic Risk, Financial Contagion, Liquidity Risk, Interbank Market, Network Model.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 1971

Authors: Sotirios Raptis

Abstract:

Health and Social care (HSc) services planning and scheduling are facing unprecedented challenges, due to the pandemic pressure and also suffer from unplanned spending that is negatively impacted by the global financial crisis. Data-driven approaches can help to improve policies, plan and design services provision schedules using algorithms that assist healthcare managers to face unexpected demands using fewer resources. The paper discusses services packing using statistical significance tests and machine learning (ML) to evaluate demands similarity and coupling. This is achieved by predicting the range of the demand (class) using ML methods such as Classification and Regression Trees (CART), Random Forests (RF), and Logistic Regression (LGR). The significance tests Chi-Squared and Student’s test are used on data over a 39 years span for which data exist for services delivered in Scotland. The demands are associated using probabilities and are parts of statistical hypotheses. These hypotheses, as their NULL part, assume that the target demand is statistically dependent on other services’ demands. This linking is checked using the data. In addition, ML methods are used to linearly predict the above target demands from the statistically found associations and extend the linear dependence of the target’s demand to independent demands forming, thus, groups of services. Statistical tests confirmed ML coupling and made the prediction statistically meaningful and proved that a target service can be matched reliably to other services while ML showed that such marked relationships can also be linear ones. Zero padding was used for missing years records and illustrated better such relationships both for limited years and for the entire span offering long-term data visualizations while limited years periods explained how well patients numbers can be related in short periods of time or that they can change over time as opposed to behaviours across more years. The prediction performance of the associations were measured using metrics such as Receiver Operating Characteristic (ROC), Area Under Curve (AUC) and Accuracy (ACC) as well as the statistical tests Chi-Squared and Student. Co-plots and comparison tables for the RF, CART, and LGR methods as well as the p-value from tests and Information Exchange (IE/MIE) measures are provided showing the relative performance of ML methods and of the statistical tests as well as the behaviour using different learning ratios. The impact of k-neighbours classification (k-NN), Cross-Correlation (CC) and C-Means (CM) first groupings was also studied over limited years and for the entire span. It was found that CART was generally behind RF and LGR but in some interesting cases, LGR reached an AUC = 0 falling below CART, while the ACC was as high as 0.912 showing that ML methods can be confused by zero-padding or by data’s irregularities or by the outliers. On average, 3 linear predictors were sufficient, LGR was found competing well RF and CART followed with the same performance at higher learning ratios. Services were packed only when a significance level (p-value) of their association coefficient was more than 0.05. Social factors relationships were observed between home care services and treatment of old people, low birth weights, alcoholism, drug abuse, and emergency admissions. The work found  that different HSc services can be well packed as plans of limited duration, across various services sectors, learning configurations, as confirmed by using statistical hypotheses.

Keywords: Class, cohorts, data frames, grouping, prediction, probabilities, services.

Procedia APA BibTeX Chicago EndNote Harvard JSON MLA RIS XML ISO 690 PDF Downloads 383